Community benchmarks

Compare

Put two chips, runtimes, or runtime versions side by side. Everything else is held fixed or called out, so a ratio is worth exactly what the matched runs say.

Add your benchmark

Runs compared: 247
Like-for-like pairs: 42
Chips available: 17

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

129 runs vs 118 runs · 42 like-for-like pairs

Held fixedPrefill: PP512Decode: TG128

These figures mix different models. Pick a model for a like-for-like comparison.
A side mixes quantisations. Pick a quantisation to compare the same weights.
The sides differ in cooldown, conditioning, decode workload, harness schema. Ratios may reflect benchmark protocol rather than the chip.

Chip comparison

Apple M5 Pro vs Apple M1 Max

Ratios read side A relative to side B. Geometric mean over 42 like-for-like pairs.

Decode: 1.08×+7.5%
Prefill: 3.02×+202%

Side A

Apple M5 Pro

129 runs

2 contributors

Latest 18 Sep 2026

Decode · TG128: 72.8tok/s median
best 2,068.0 · worst 10.6
Prefill · PP512: 1,852tok/s median
best 190,107 · worst 327

Models: gemma-3-1b-it, gemma-4-26B-A4B-it, gemma-4-E2B-it, gemma-4-E4B-it, Gemma-4-E4B-It, gpt-oss-20b, Gpt-Oss-20B, Llama 3.2 3B Instruct, Llama-3.1-8B-Instruct, Llama-3.2-1B-Instruct, Llama-3.2-3B-Instruct, Mistral-7B-Instruct-v0.3, Muse-Glimmer-30B, NVIDIA-Nemotron-3-Nano-30B-A3B, Qwen3-0.6B, Qwen3-1.7B, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Thinking-2507, Qwen3-4B, Qwen3-4B-Instruct-2507, Qwen3-4B-Thinking-2507, Qwen3-8B, Qwen3-8B-base-q2, Qwen3-8B-base-q3, Qwen3-8B-base-q5, Qwen3-8B-base-q6, Qwen3.5-2B, Qwen3.5-2B-Base, Qwen3.5-35B-A3B, Qwen3.6-27B, Qwen3.6-35B-A3B, Qwen3.8-27B, Tinystories Lay8 Hs512 Hd8 33M, tinystories-lay8-hs512-hd8-33M
Runtimes: BaseRTllama.cpp
Versions: BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)
Quantisations: BF16, F16, mxfp4, passthrough_gguf, Q2, Q2_K, Q3, Q3_K_M, Q4, Q4_0, Q4_1, Q4_K_M, Q5, Q5_K_M, Q6, Q6_K, Q8, Q8_0
Backends: BLAS + Metal, Metal
Cooldown: off, on
Conditioning: idle_reset_then_warm, runtime_native_warmup, warmup_only
Decode workload: TG128, TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1, computearena-measurements/1

Side B

Apple M1 Max

118 runs

1 contributor

Latest 14 Oct 2026

Decode · TG128: 75.5tok/s median
best 366.4 · worst 10.9
Prefill · PP512: 881tok/s median
best 5,884 · worst 80

Models: gemma-3-1b-it-Q4, gemma-3-1b-it-Q8, gemma-4-26B-A4B-it-Q4, gemma-4-26B-A4B-it-Q8, gemma-4-E2B-it-Q4, gemma-4-E2B-it-Q8, gemma-4-E4B-it-Q4, gemma-4-E4B-it-Q8, gpt-oss-20b-MXFP4, gpt-oss-20b-Q4, gpt-oss-20b-Q8, Llama-3.1-8B-Instruct-Q4, Llama-3.1-8B-Instruct-Q8, Llama-3.2-1B-Instruct-Q4, Llama-3.2-1B-Instruct-Q8, Llama-3.2-3B-Instruct-Q4, Llama-3.2-3B-Instruct-Q8, Mistral-7B-Instruct-v0.3-Q4, Mistral-7B-Instruct-v0.3-Q8, muse-glimmer-30B-kquant-17gb, muse-glimmer-30B-kquant-dynamic, NVIDIA-Nemotron-3-Nano-30B-A3B-Q4, NVIDIA-Nemotron-3-Nano-30B-A3B-Q8, Qwen3-0.6B-Q4, Qwen3-0.6B-Q8, Qwen3-1.7B-Q4, Qwen3-1.7B-Q8, Qwen3-30B-A3B-Instruct-2507-Q4, Qwen3-30B-A3B-Thinking-2507-Q4, Qwen3-30B-A3B-Thinking-2507-Q8, Qwen3-4B-Instruct-2507-Q4, Qwen3-4B-Instruct-2507-Q8, Qwen3-4B-Q4, Qwen3-4B-Q8, Qwen3-4B-Thinking-2507-Q4, Qwen3-4B-Thinking-2507-Q8, Qwen3-8B-Q4, Qwen3-8B-Q8, Qwen3.5-2B-Base-Q4, Qwen3.5-2B-Base-Q8, Qwen3.5-2B-Q4, Qwen3.5-2B-Q8, Qwen3.5-35B-A3B-Q4, Qwen3.5-35B-A3B-Q8, Qwen3.6-27B-Q4, Qwen3.6-27B-Q8, Qwen3.6-35B-A3B-Q4, Qwen3.6-35B-A3B-Q8, Qwen3.8-27B-Q4, Qwen3.8-27B-Q4-mtp, Qwen3.8-27B-Q8
Runtimes: BaseRT
Versions: BaseRT 0.2.6, BaseRT 0.3.0
Quantisations: mxfp4, passthrough_gguf, Q4, Q8
Backends: Metal
Cooldown: off
Conditioning: warmup_only
Decode workload: TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1

What differs besides the chip

Facet	Apple M5 Pro	Apple M1 Max
Model	gemma-3-1b-it, gemma-4-26B-A4B-it, gemma-4-E2B-it, gemma-4-E4B-it, Gemma-4-E4B-It, gpt-oss-20b, Gpt-Oss-20B, Llama 3.2 3B Instruct, Llama-3.1-8B-Instruct, Llama-3.2-1B-Instruct, Llama-3.2-3B-Instruct, Mistral-7B-Instruct-v0.3, Muse-Glimmer-30B, NVIDIA-Nemotron-3-Nano-30B-A3B, Qwen3-0.6B, Qwen3-1.7B, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Thinking-2507, Qwen3-4B, Qwen3-4B-Instruct-2507, Qwen3-4B-Thinking-2507, Qwen3-8B, Qwen3-8B-base-q2, Qwen3-8B-base-q3, Qwen3-8B-base-q5, Qwen3-8B-base-q6, Qwen3.5-2B, Qwen3.5-2B-Base, Qwen3.5-35B-A3B, Qwen3.6-27B, Qwen3.6-35B-A3B, Qwen3.8-27B, Tinystories Lay8 Hs512 Hd8 33M, tinystories-lay8-hs512-hd8-33M	gemma-3-1b-it-Q4, gemma-3-1b-it-Q8, gemma-4-26B-A4B-it-Q4, gemma-4-26B-A4B-it-Q8, gemma-4-E2B-it-Q4, gemma-4-E2B-it-Q8, gemma-4-E4B-it-Q4, gemma-4-E4B-it-Q8, gpt-oss-20b-MXFP4, gpt-oss-20b-Q4, gpt-oss-20b-Q8, Llama-3.1-8B-Instruct-Q4, Llama-3.1-8B-Instruct-Q8, Llama-3.2-1B-Instruct-Q4, Llama-3.2-1B-Instruct-Q8, Llama-3.2-3B-Instruct-Q4, Llama-3.2-3B-Instruct-Q8, Mistral-7B-Instruct-v0.3-Q4, Mistral-7B-Instruct-v0.3-Q8, muse-glimmer-30B-kquant-17gb, muse-glimmer-30B-kquant-dynamic, NVIDIA-Nemotron-3-Nano-30B-A3B-Q4, NVIDIA-Nemotron-3-Nano-30B-A3B-Q8, Qwen3-0.6B-Q4, Qwen3-0.6B-Q8, Qwen3-1.7B-Q4, Qwen3-1.7B-Q8, Qwen3-30B-A3B-Instruct-2507-Q4, Qwen3-30B-A3B-Thinking-2507-Q4, Qwen3-30B-A3B-Thinking-2507-Q8, Qwen3-4B-Instruct-2507-Q4, Qwen3-4B-Instruct-2507-Q8, Qwen3-4B-Q4, Qwen3-4B-Q8, Qwen3-4B-Thinking-2507-Q4, Qwen3-4B-Thinking-2507-Q8, Qwen3-8B-Q4, Qwen3-8B-Q8, Qwen3.5-2B-Base-Q4, Qwen3.5-2B-Base-Q8, Qwen3.5-2B-Q4, Qwen3.5-2B-Q8, Qwen3.5-35B-A3B-Q4, Qwen3.5-35B-A3B-Q8, Qwen3.6-27B-Q4, Qwen3.6-27B-Q8, Qwen3.6-35B-A3B-Q4, Qwen3.6-35B-A3B-Q8, Qwen3.8-27B-Q4, Qwen3.8-27B-Q4-mtp, Qwen3.8-27B-Q8
Runtime	BaseRT, llama.cpp	BaseRT
Runtime version	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)	BaseRT 0.2.6, BaseRT 0.3.0
Quantisation	BF16, F16, mxfp4, passthrough_gguf, Q2, Q2_K, Q3, Q3_K_M, Q4, Q4_0, Q4_1, Q4_K_M, Q5, Q5_K_M, Q6, Q6_K, Q8, Q8_0	mxfp4, passthrough_gguf, Q4, Q8
Backend	BLAS + Metal, Metal	Metal
Cooldown	off, on	off
Conditioning	idle_reset_then_warm, runtime_native_warmup, warmup_only	warmup_only
Decode workload	TG128, TG128 @ 1 ctx	TG128 @ 1 ctx
Harness schema	basert-benchmark-harness/1, computearena-measurements/1	basert-benchmark-harness/1

Like-for-like pairs

Each row is a configuration present on both sides. Values are per-cell medians; ratios read Apple M5 Pro relative to Apple M1 Max.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Llama-3.2-3B-Instruct BaseRTQ4	94.6	98.6	0.96×	4,297	1,238	3.47×	5 / 4
Qwen3-8B BaseRTQ4	59.7	60.2	0.99×	1,761	507	3.47×	7 / 2
Llama-3.1-8B-Instruct BaseRTQ4	48.8	51.1	0.95×	1,784	509	3.50×	4 / 4
Qwen3.8-27B BaseRTQ4	13.5	14.6	0.93×	341	82	4.16×	2 / 6
Llama-3.2-1B-Instruct BaseRTQ4	206.3	235.5	0.88×	11,673	3,353	3.48×	3 / 4
Mistral-7B-Instruct-v0.3 BaseRTQ4	51.7	53.5	0.97×	1,789	510	3.51×	2 / 4
Muse-Glimmer-30B BaseRTpassthrough_gguf	15.7	15.8	0.99×	480	138	3.48×	2 / 4
Qwen3-0.6B BaseRTQ4	512.0	233.6	2.19×	20,603	3,856	5.34×	3 / 2
Qwen3-0.6B BaseRTQ8	349.8	191.1	1.83×	20,366	4,054	5.02×	3 / 2
gemma-3-1b-it BaseRTQ4	281.7	216.8	1.30×	14,392	4,100	3.51×	2 / 2
gemma-4-E4B-it BaseRTQ4	82.3	75.5	1.09×	4,646	1,388	3.35×	2 / 2
gemma-4-E4B-it BaseRTQ8	51.2	51.6	0.99×	4,476	1,369	3.27×	2 / 2
gpt-oss-20b BaseRTQ4	110.5	81.8	1.35×	1,156	882	1.31×	2 / 2
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ8	66.0	60.6	1.09×	1,748	857	2.04×	1 / 3
Qwen3-1.7B BaseRTQ4	222.9	220.0	1.01×	7,654	2,237	3.42×	2 / 2
Qwen3-1.7B BaseRTQ8	132.4	153.7	0.86×	7,655	2,217	3.45×	2 / 2
Qwen3-30B-A3B-Instruct-2507 BaseRTQ4	98.1	87.6	1.12×	3,493	901	3.87×	2 / 2
Qwen3-30B-A3B-Thinking-2507 BaseRTQ8	65.1	64.5	1.01×	3,692	893	4.13×	1 / 3
Qwen3-4B BaseRTQ4	105.6	103.1	1.02×	3,378	926	3.65×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ4	89.9	90.8	0.99×	3,345	922	3.63×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ8	63.5	71.8	0.89×	3,402	924	3.68×	2 / 2
Qwen3-8B BaseRTQ8	34.9	38.2	0.91×	1,746	500	3.49×	2 / 2
gemma-3-1b-it BaseRTQ8	210.3	168.6	1.25×	15,061	4,118	3.66×	1 / 2
gemma-4-26B-A4B-it BaseRTQ4	51.7	51.6	1.00×	2,047	871	2.35×	1 / 2
gemma-4-26B-A4B-it BaseRTQ8	51.4	45.0	1.14×	3,253	876	3.71×	1 / 2
gemma-4-E2B-it BaseRTQ4	144.6	119.5	1.21×	13,240	4,522	2.93×	1 / 2
gemma-4-E2B-it BaseRTQ8	96.0	90.3	1.06×	12,646	4,414	2.87×	1 / 2
gpt-oss-20b BaseRTQ8	100.6	75.7	1.33×	1,065	874	1.22×	1 / 2
gpt-oss-20b BaseRTmxfp4	103.6	76.2	1.36×	1,013	890	1.14×	1 / 2
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ4	100.1	109.7	0.91×	2,499	862	2.90×	1 / 2
Qwen3-30B-A3B-Thinking-2507 BaseRTQ4	104.4	86.8	1.20×	3,694	902	4.09×	1 / 2
Qwen3-4B BaseRTQ8	64.7	71.3	0.91×	3,412	919	3.71×	1 / 2
Qwen3-4B-Thinking-2507 BaseRTQ4	91.6	91.3	1.00×	3,363	923	3.64×	1 / 2
Qwen3-4B-Thinking-2507 BaseRTQ8	64.7	71.5	0.91×	3,414	922	3.70×	1 / 2
Qwen3.5-2B BaseRTQ4	217.7	188.8	1.15×	2,641	1,263	2.09×	1 / 2
Qwen3.5-2B BaseRTQ8	130.7	140.3	0.93×	2,638	1,235	2.14×	1 / 2
Qwen3.5-2B-Base BaseRTQ4	218.2	189.3	1.15×	2,645	1,271	2.08×	1 / 2
Qwen3.5-2B-Base BaseRTQ8	131.4	140.6	0.93×	2,642	1,253	2.11×	1 / 2
Qwen3.5-35B-A3B BaseRTQ4	113.4	93.2	1.22×	1,304	580	2.25×	1 / 2
Qwen3.6-27B BaseRTQ4	16.1	17.9	0.90×	364	112	3.26×	1 / 2
Qwen3.6-27B BaseRTQ8	10.6	11.0	0.96×	355	112	3.16×	1 / 2
Qwen3.6-35B-A3B BaseRTQ4	113.2	92.9	1.22×	1,275	568	2.25×	1 / 2

Side A · Apple M5 Pro

Top 25 of 129 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
ivnle/tinystories-lay8-hs512-hd8-33M BaseRT 0.2.4Q4	Apple M5 Pro Metal	2,068.0 TG128	190,107 PP512	arki05	17 Sep 2026	View Benchmark
Tinystories Lay8 Hs512 Hd8 33M llama.cpp b10809 (5266f24da)Q4_0	Apple M5 Pro BLAS + Metal	1,443.3 TG128	124,181 PP512	arki05	17 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q4	Apple M5 Pro Metal	516.8 TG128	20,778 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q4	Apple M5 Pro Metal	512.0 TG128	20,603 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.5Q4	Apple M5 Pro Metal	481.5 TG128 @ 1 ctx	19,595 PP512	isu	18 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	358.3 TG128	14,509 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	358.1 TG128	14,344 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	356.2 TG128	14,552 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8	Apple M5 Pro Metal	350.2 TG128	20,537 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8	Apple M5 Pro Metal	349.8 TG128	20,366 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8	Apple M5 Pro Metal	311.0 TG128	18,474 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-3-1b-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	293.1 TG128	15,066 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q8_0	Apple M5 Pro BLAS + Metal	283.0 TG128	14,942 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-3-1b-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	270.4 TG128	13,717 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q4	Apple M5 Pro Metal	235.4 TG128	8,040 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	229.1 TG128	11,673 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B-Base BaseRT 0.2.4Q4	Apple M5 Pro Metal	218.2 TG128	2,645 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B BaseRT 0.2.4Q4	Apple M5 Pro Metal	217.7 TG128	2,641 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q4	Apple M5 Pro Metal	210.3 TG128	7,268 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-3-1b-it BaseRT 0.2.4Q8	Apple M5 Pro Metal	210.3 TG128	15,061 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	206.3 TG128	10,528 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	205.3 TG128	12,067 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-4-E2B-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	144.6 TG128	13,240 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q8	Apple M5 Pro Metal	139.7 TG128	8,043 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B-Base BaseRT 0.2.4Q8	Apple M5 Pro Metal	131.4 TG128	2,642 PP512	arki05	11 Sep 2026	View Benchmark

Side B · Apple M1 Max

Top 25 of 118 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-0.6B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	366.4 TG128 @ 1 ctx	5,861 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	307.9 TG128 @ 1 ctx	5,884 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	242.1 TG128 @ 1 ctx	3,333 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	238.3 TG128 @ 1 ctx	3,348 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.3.0Q4	Apple M1 Max Metal	232.7 TG128 @ 1 ctx	3,357 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	229.4 TG128 @ 1 ctx	3,372 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	220.2 TG128 @ 1 ctx	2,230 PP512	basecompute	9 Oct 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	220.0 TG128 @ 1 ctx	4,102 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	219.7 TG128 @ 1 ctx	2,244 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	213.6 TG128 @ 1 ctx	4,098 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	192.9 TG128 @ 1 ctx	429 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	190.0 TG128 @ 1 ctx	439 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	188.7 TG128 @ 1 ctx	2,102 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	188.6 TG128 @ 1 ctx	2,105 PP512	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	188.3 TG128 @ 1 ctx	2,109 PP512	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	184.7 TG128 @ 1 ctx	2,096 PP512	basecompute	9 Oct 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	170.0 TG128 @ 1 ctx	4,120 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	167.3 TG128 @ 1 ctx	4,116 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	153.9 TG128 @ 1 ctx	2,223 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	153.6 TG128 @ 1 ctx	2,210 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	141.5 TG128 @ 1 ctx	400 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	140.7 TG128 @ 1 ctx	438 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	140.5 TG128 @ 1 ctx	2,068 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	139.1 TG128 @ 1 ctx	2,070 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	138.5 TG128 @ 1 ctx	2,059 PP512	basecompute	14 Oct 2026	View Benchmark

Compare

Loading community benchmarks…

What differs besides the chip

Facet	Apple M5 Pro	Apple M1 Max
Model	gemma-3-1b-it, gemma-4-26B-A4B-it, gemma-4-E2B-it, gemma-4-E4B-it, Gemma-4-E4B-It, gpt-oss-20b, Gpt-Oss-20B, Llama 3.2 3B Instruct, Llama-3.1-8B-Instruct, Llama-3.2-1B-Instruct, Llama-3.2-3B-Instruct, Mistral-7B-Instruct-v0.3, Muse-Glimmer-30B, NVIDIA-Nemotron-3-Nano-30B-A3B, Qwen3-0.6B, Qwen3-1.7B, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Thinking-2507, Qwen3-4B, Qwen3-4B-Instruct-2507, Qwen3-4B-Thinking-2507, Qwen3-8B, Qwen3-8B-base-q2, Qwen3-8B-base-q3, Qwen3-8B-base-q5, Qwen3-8B-base-q6, Qwen3.5-2B, Qwen3.5-2B-Base, Qwen3.5-35B-A3B, Qwen3.6-27B, Qwen3.6-35B-A3B, Qwen3.8-27B, Tinystories Lay8 Hs512 Hd8 33M, tinystories-lay8-hs512-hd8-33M	gemma-3-1b-it-Q4, gemma-3-1b-it-Q8, gemma-4-26B-A4B-it-Q4, gemma-4-26B-A4B-it-Q8, gemma-4-E2B-it-Q4, gemma-4-E2B-it-Q8, gemma-4-E4B-it-Q4, gemma-4-E4B-it-Q8, gpt-oss-20b-MXFP4, gpt-oss-20b-Q4, gpt-oss-20b-Q8, Llama-3.1-8B-Instruct-Q4, Llama-3.1-8B-Instruct-Q8, Llama-3.2-1B-Instruct-Q4, Llama-3.2-1B-Instruct-Q8, Llama-3.2-3B-Instruct-Q4, Llama-3.2-3B-Instruct-Q8, Mistral-7B-Instruct-v0.3-Q4, Mistral-7B-Instruct-v0.3-Q8, muse-glimmer-30B-kquant-17gb, muse-glimmer-30B-kquant-dynamic, NVIDIA-Nemotron-3-Nano-30B-A3B-Q4, NVIDIA-Nemotron-3-Nano-30B-A3B-Q8, Qwen3-0.6B-Q4, Qwen3-0.6B-Q8, Qwen3-1.7B-Q4, Qwen3-1.7B-Q8, Qwen3-30B-A3B-Instruct-2507-Q4, Qwen3-30B-A3B-Thinking-2507-Q4, Qwen3-30B-A3B-Thinking-2507-Q8, Qwen3-4B-Instruct-2507-Q4, Qwen3-4B-Instruct-2507-Q8, Qwen3-4B-Q4, Qwen3-4B-Q8, Qwen3-4B-Thinking-2507-Q4, Qwen3-4B-Thinking-2507-Q8, Qwen3-8B-Q4, Qwen3-8B-Q8, Qwen3.5-2B-Base-Q4, Qwen3.5-2B-Base-Q8, Qwen3.5-2B-Q4, Qwen3.5-2B-Q8, Qwen3.5-35B-A3B-Q4, Qwen3.5-35B-A3B-Q8, Qwen3.6-27B-Q4, Qwen3.6-27B-Q8, Qwen3.6-35B-A3B-Q4, Qwen3.6-35B-A3B-Q8, Qwen3.8-27B-Q4, Qwen3.8-27B-Q4-mtp, Qwen3.8-27B-Q8
Runtime	BaseRT, llama.cpp	BaseRT
Runtime version	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)	BaseRT 0.2.6, BaseRT 0.3.0
Quantisation	BF16, F16, mxfp4, passthrough_gguf, Q2, Q2_K, Q3, Q3_K_M, Q4, Q4_0, Q4_1, Q4_K_M, Q5, Q5_K_M, Q6, Q6_K, Q8, Q8_0	mxfp4, passthrough_gguf, Q4, Q8
Backend	BLAS + Metal, Metal	Metal
Cooldown	off, on	off
Conditioning	idle_reset_then_warm, runtime_native_warmup, warmup_only	warmup_only
Decode workload	TG128, TG128 @ 1 ctx	TG128 @ 1 ctx
Harness schema	basert-benchmark-harness/1, computearena-measurements/1	basert-benchmark-harness/1

Like-for-like pairs

Each row is a configuration present on both sides. Values are per-cell medians; ratios read Apple M5 Pro relative to Apple M1 Max.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Llama-3.2-3B-Instruct BaseRTQ4	94.6	98.6	0.96×	4,297	1,238	3.47×	5 / 4
Qwen3-8B BaseRTQ4	59.7	60.2	0.99×	1,761	507	3.47×	7 / 2
Llama-3.1-8B-Instruct BaseRTQ4	48.8	51.1	0.95×	1,784	509	3.50×	4 / 4
Qwen3.8-27B BaseRTQ4	13.5	14.6	0.93×	341	82	4.16×	2 / 6
Llama-3.2-1B-Instruct BaseRTQ4	206.3	235.5	0.88×	11,673	3,353	3.48×	3 / 4
Mistral-7B-Instruct-v0.3 BaseRTQ4	51.7	53.5	0.97×	1,789	510	3.51×	2 / 4
Muse-Glimmer-30B BaseRTpassthrough_gguf	15.7	15.8	0.99×	480	138	3.48×	2 / 4
Qwen3-0.6B BaseRTQ4	512.0	233.6	2.19×	20,603	3,856	5.34×	3 / 2
Qwen3-0.6B BaseRTQ8	349.8	191.1	1.83×	20,366	4,054	5.02×	3 / 2
gemma-3-1b-it BaseRTQ4	281.7	216.8	1.30×	14,392	4,100	3.51×	2 / 2
gemma-4-E4B-it BaseRTQ4	82.3	75.5	1.09×	4,646	1,388	3.35×	2 / 2
gemma-4-E4B-it BaseRTQ8	51.2	51.6	0.99×	4,476	1,369	3.27×	2 / 2
gpt-oss-20b BaseRTQ4	110.5	81.8	1.35×	1,156	882	1.31×	2 / 2
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ8	66.0	60.6	1.09×	1,748	857	2.04×	1 / 3
Qwen3-1.7B BaseRTQ4	222.9	220.0	1.01×	7,654	2,237	3.42×	2 / 2
Qwen3-1.7B BaseRTQ8	132.4	153.7	0.86×	7,655	2,217	3.45×	2 / 2
Qwen3-30B-A3B-Instruct-2507 BaseRTQ4	98.1	87.6	1.12×	3,493	901	3.87×	2 / 2
Qwen3-30B-A3B-Thinking-2507 BaseRTQ8	65.1	64.5	1.01×	3,692	893	4.13×	1 / 3
Qwen3-4B BaseRTQ4	105.6	103.1	1.02×	3,378	926	3.65×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ4	89.9	90.8	0.99×	3,345	922	3.63×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ8	63.5	71.8	0.89×	3,402	924	3.68×	2 / 2
Qwen3-8B BaseRTQ8	34.9	38.2	0.91×	1,746	500	3.49×	2 / 2
gemma-3-1b-it BaseRTQ8	210.3	168.6	1.25×	15,061	4,118	3.66×	1 / 2
gemma-4-26B-A4B-it BaseRTQ4	51.7	51.6	1.00×	2,047	871	2.35×	1 / 2
gemma-4-26B-A4B-it BaseRTQ8	51.4	45.0	1.14×	3,253	876	3.71×	1 / 2
gemma-4-E2B-it BaseRTQ4	144.6	119.5	1.21×	13,240	4,522	2.93×	1 / 2
gemma-4-E2B-it BaseRTQ8	96.0	90.3	1.06×	12,646	4,414	2.87×	1 / 2
gpt-oss-20b BaseRTQ8	100.6	75.7	1.33×	1,065	874	1.22×	1 / 2
gpt-oss-20b BaseRTmxfp4	103.6	76.2	1.36×	1,013	890	1.14×	1 / 2
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ4	100.1	109.7	0.91×	2,499	862	2.90×	1 / 2
Qwen3-30B-A3B-Thinking-2507 BaseRTQ4	104.4	86.8	1.20×	3,694	902	4.09×	1 / 2
Qwen3-4B BaseRTQ8	64.7	71.3	0.91×	3,412	919	3.71×	1 / 2
Qwen3-4B-Thinking-2507 BaseRTQ4	91.6	91.3	1.00×	3,363	923	3.64×	1 / 2
Qwen3-4B-Thinking-2507 BaseRTQ8	64.7	71.5	0.91×	3,414	922	3.70×	1 / 2
Qwen3.5-2B BaseRTQ4	217.7	188.8	1.15×	2,641	1,263	2.09×	1 / 2
Qwen3.5-2B BaseRTQ8	130.7	140.3	0.93×	2,638	1,235	2.14×	1 / 2
Qwen3.5-2B-Base BaseRTQ4	218.2	189.3	1.15×	2,645	1,271	2.08×	1 / 2
Qwen3.5-2B-Base BaseRTQ8	131.4	140.6	0.93×	2,642	1,253	2.11×	1 / 2
Qwen3.5-35B-A3B BaseRTQ4	113.4	93.2	1.22×	1,304	580	2.25×	1 / 2
Qwen3.6-27B BaseRTQ4	16.1	17.9	0.90×	364	112	3.26×	1 / 2
Qwen3.6-27B BaseRTQ8	10.6	11.0	0.96×	355	112	3.16×	1 / 2
Qwen3.6-35B-A3B BaseRTQ4	113.2	92.9	1.22×	1,275	568	2.25×	1 / 2

Side A · Apple M5 Pro

Top 25 of 129 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
ivnle/tinystories-lay8-hs512-hd8-33M BaseRT 0.2.4Q4	Apple M5 Pro Metal	2,068.0 TG128	190,107 PP512	arki05	17 Sep 2026	View Benchmark
Tinystories Lay8 Hs512 Hd8 33M llama.cpp b10809 (5266f24da)Q4_0	Apple M5 Pro BLAS + Metal	1,443.3 TG128	124,181 PP512	arki05	17 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q4	Apple M5 Pro Metal	516.8 TG128	20,778 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q4	Apple M5 Pro Metal	512.0 TG128	20,603 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.5Q4	Apple M5 Pro Metal	481.5 TG128 @ 1 ctx	19,595 PP512	isu	18 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	358.3 TG128	14,509 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	358.1 TG128	14,344 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	356.2 TG128	14,552 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8	Apple M5 Pro Metal	350.2 TG128	20,537 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8	Apple M5 Pro Metal	349.8 TG128	20,366 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8	Apple M5 Pro Metal	311.0 TG128	18,474 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-3-1b-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	293.1 TG128	15,066 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q8_0	Apple M5 Pro BLAS + Metal	283.0 TG128	14,942 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-3-1b-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	270.4 TG128	13,717 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q4	Apple M5 Pro Metal	235.4 TG128	8,040 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	229.1 TG128	11,673 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B-Base BaseRT 0.2.4Q4	Apple M5 Pro Metal	218.2 TG128	2,645 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B BaseRT 0.2.4Q4	Apple M5 Pro Metal	217.7 TG128	2,641 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q4	Apple M5 Pro Metal	210.3 TG128	7,268 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-3-1b-it BaseRT 0.2.4Q8	Apple M5 Pro Metal	210.3 TG128	15,061 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	206.3 TG128	10,528 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	205.3 TG128	12,067 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-4-E2B-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	144.6 TG128	13,240 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q8	Apple M5 Pro Metal	139.7 TG128	8,043 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B-Base BaseRT 0.2.4Q8	Apple M5 Pro Metal	131.4 TG128	2,642 PP512	arki05	11 Sep 2026	View Benchmark

Side B · Apple M1 Max

Top 25 of 118 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-0.6B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	366.4 TG128 @ 1 ctx	5,861 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	307.9 TG128 @ 1 ctx	5,884 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	242.1 TG128 @ 1 ctx	3,333 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	238.3 TG128 @ 1 ctx	3,348 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.3.0Q4	Apple M1 Max Metal	232.7 TG128 @ 1 ctx	3,357 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	229.4 TG128 @ 1 ctx	3,372 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	220.2 TG128 @ 1 ctx	2,230 PP512	basecompute	9 Oct 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	220.0 TG128 @ 1 ctx	4,102 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	219.7 TG128 @ 1 ctx	2,244 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	213.6 TG128 @ 1 ctx	4,098 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	192.9 TG128 @ 1 ctx	429 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	190.0 TG128 @ 1 ctx	439 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	188.7 TG128 @ 1 ctx	2,102 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	188.6 TG128 @ 1 ctx	2,105 PP512	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	188.3 TG128 @ 1 ctx	2,109 PP512	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	184.7 TG128 @ 1 ctx	2,096 PP512	basecompute	9 Oct 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	170.0 TG128 @ 1 ctx	4,120 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	167.3 TG128 @ 1 ctx	4,116 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	153.9 TG128 @ 1 ctx	2,223 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	153.6 TG128 @ 1 ctx	2,210 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	141.5 TG128 @ 1 ctx	400 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	140.7 TG128 @ 1 ctx	438 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	140.5 TG128 @ 1 ctx	2,068 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	139.1 TG128 @ 1 ctx	2,070 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q8 BaseRT 0.3.0Q8	Apple M1 Max Metal	138.5 TG128 @ 1 ctx	2,059 PP512	basecompute	14 Oct 2026	View Benchmark