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: 199
Like-for-like pairs: 29
Chips available: 17

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

70 runs vs 129 runs · 29 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 M4 Pro vs Apple M5 Pro

Ratios read side A relative to side B. Geometric mean over 29 like-for-like pairs.

Decode: 0.84×-16.4%
Prefill: 0.29×-71.0%

Side A

Apple M4 Pro

70 runs

1 contributor

Latest 14 Oct 2026

Decode · TG128: 83.8tok/s median
best 401.9 · worst 31.5
Prefill · PP512: 1,077tok/s median
best 5,025 · worst 391

Models: gemma-3-1b-it-Q4, gemma-3-1b-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, Qwen3-0.6B-Q4, Qwen3-0.6B-Q8, Qwen3-1.7B-Q4, Qwen3-1.7B-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
Runtimes: BaseRT
Versions: BaseRT 0.2.6, BaseRT 0.3.0
Quantisations: mxfp4, Q4, Q8
Backends: Metal
Cooldown: off
Conditioning: warmup_only
Decode workload: TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1

Side B

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

What differs besides the chip

Facet	Apple M4 Pro	Apple M5 Pro
Model	gemma-3-1b-it-Q4, gemma-3-1b-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, Qwen3-0.6B-Q4, Qwen3-0.6B-Q8, Qwen3-1.7B-Q4, Qwen3-1.7B-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	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
Runtime	BaseRT	BaseRT, llama.cpp
Runtime version	BaseRT 0.2.6, BaseRT 0.3.0	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)
Quantisation	mxfp4, Q4, Q8	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
Backend	Metal	BLAS + Metal, Metal
Cooldown	off	off, on
Conditioning	warmup_only	idle_reset_then_warm, runtime_native_warmup, warmup_only
Decode workload	TG128 @ 1 ctx	TG128, TG128 @ 1 ctx
Harness schema	basert-benchmark-harness/1	basert-benchmark-harness/1, computearena-measurements/1

Like-for-like pairs

Each row is a configuration present on both sides. Values are per-cell medians; ratios read Apple M4 Pro relative to Apple M5 Pro.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Llama-3.2-3B-Instruct BaseRTQ4	82.9	94.6	0.88×	938	4,297	0.22×	4 / 5
Qwen3-8B BaseRTQ4	52.5	59.7	0.88×	397	1,761	0.23×	2 / 7
Llama-3.1-8B-Instruct BaseRTQ4	43.9	48.8	0.90×	393	1,784	0.22×	4 / 4
Llama-3.2-1B-Instruct BaseRTQ4	189.2	206.3	0.92×	2,688	11,673	0.23×	4 / 3
Mistral-7B-Instruct-v0.3 BaseRTQ4	46.2	51.7	0.89×	392	1,789	0.22×	4 / 2
Qwen3-0.6B BaseRTQ4	305.2	512.0	0.60×	4,298	20,603	0.21×	2 / 3
Qwen3-0.6B BaseRTQ8	291.7	349.8	0.83×	4,816	20,366	0.24×	2 / 3
gemma-3-1b-it BaseRTQ4	222.8	281.7	0.79×	3,400	14,392	0.24×	2 / 2
gemma-4-E4B-it BaseRTQ4	68.9	82.3	0.84×	1,098	4,646	0.24×	2 / 2
gemma-4-E4B-it BaseRTQ8	44.3	51.2	0.87×	1,077	4,476	0.24×	2 / 2
gpt-oss-20b BaseRTQ4	78.9	110.5	0.71×	732	1,156	0.63×	2 / 2
Qwen3-1.7B BaseRTQ4	191.9	222.9	0.86×	1,825	7,654	0.24×	2 / 2
Qwen3-1.7B BaseRTQ8	125.3	132.4	0.95×	1,820	7,655	0.24×	2 / 2
Qwen3-4B BaseRTQ4	89.8	105.6	0.85×	734	3,378	0.22×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ4	77.9	89.9	0.87×	726	3,345	0.22×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ8	56.1	63.5	0.88×	728	3,402	0.21×	2 / 2
Qwen3-8B BaseRTQ8	31.6	34.9	0.91×	393	1,746	0.22×	2 / 2
gemma-3-1b-it BaseRTQ8	175.4	210.3	0.83×	3,382	15,061	0.22×	2 / 1
gemma-4-E2B-it BaseRTQ4	123.9	144.6	0.86×	3,729	13,240	0.28×	2 / 1
gemma-4-E2B-it BaseRTQ8	83.8	96.0	0.87×	3,631	12,646	0.29×	2 / 1
gpt-oss-20b BaseRTQ8	73.4	100.6	0.73×	730	1,065	0.69×	2 / 1
gpt-oss-20b BaseRTmxfp4	72.5	103.6	0.70×	736	1,013	0.73×	2 / 1
Qwen3-4B BaseRTQ8	56.0	64.7	0.87×	725	3,412	0.21×	2 / 1
Qwen3-4B-Thinking-2507 BaseRTQ4	78.1	91.6	0.85×	729	3,363	0.22×	2 / 1
Qwen3-4B-Thinking-2507 BaseRTQ8	56.2	64.7	0.87×	729	3,414	0.21×	2 / 1
Qwen3.5-2B BaseRTQ4	175.6	217.7	0.81×	1,492	2,641	0.56×	2 / 1
Qwen3.5-2B BaseRTQ8	112.9	130.7	0.86×	1,475	2,638	0.56×	2 / 1
Qwen3.5-2B-Base BaseRTQ4	174.7	218.2	0.80×	1,483	2,645	0.56×	2 / 1
Qwen3.5-2B-Base BaseRTQ8	113.6	131.4	0.86×	1,479	2,642	0.56×	2 / 1

Side A · Apple M4 Pro

Top 25 of 70 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-0.6B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	401.9 TG128 @ 1 ctx	5,025 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q8 BaseRT 0.3.0Q8	Apple M4 Pro Metal	298.7 TG128 @ 1 ctx	4,845 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	284.7 TG128 @ 1 ctx	4,787 PP512	basecompute	19 Sep 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	224.9 TG128 @ 1 ctx	3,430 PP512	basecompute	19 Sep 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	220.7 TG128 @ 1 ctx	3,369 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	208.6 TG128 @ 1 ctx	3,571 PP512	basecompute	19 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	204.6 TG128 @ 1 ctx	2,685 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	199.0 TG128 @ 1 ctx	2,679 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	193.1 TG128 @ 1 ctx	1,828 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	190.7 TG128 @ 1 ctx	1,822 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.2.6Q4	Apple M4 Pro Metal	179.3 TG128 @ 1 ctx	2,692 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	179.1 TG128 @ 1 ctx	1,150 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	178.8 TG128 @ 1 ctx	3,337 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	176.8 TG128 @ 1 ctx	1,150 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.3.0Q4	Apple M4 Pro Metal	176.8 TG128 @ 1 ctx	2,691 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	173.9 TG128 @ 1 ctx	1,810 PP512	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	172.5 TG128 @ 1 ctx	1,815 PP512	basecompute	11 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	172.3 TG128 @ 1 ctx	1,835 PP512	basecompute	14 Oct 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.3.0Q8	Apple M4 Pro Metal	172.0 TG128 @ 1 ctx	3,428 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	172.0 TG128 @ 1 ctx	1,833 PP512	basecompute	9 Oct 2026	View Benchmark
gemma-4-E2B-it-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	126.0 TG128 @ 1 ctx	3,722 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.3.0Q8	Apple M4 Pro Metal	125.3 TG128 @ 1 ctx	1,819 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	125.3 TG128 @ 1 ctx	1,822 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-4-E2B-it-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	121.8 TG128 @ 1 ctx	3,736 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	113.9 TG128 @ 1 ctx	1,149 PP512	basecompute	20 Sep 2026	View Benchmark

Side B · 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

Compare

Loading community benchmarks…

What differs besides the chip

Facet	Apple M4 Pro	Apple M5 Pro
Model	gemma-3-1b-it-Q4, gemma-3-1b-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, Qwen3-0.6B-Q4, Qwen3-0.6B-Q8, Qwen3-1.7B-Q4, Qwen3-1.7B-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	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
Runtime	BaseRT	BaseRT, llama.cpp
Runtime version	BaseRT 0.2.6, BaseRT 0.3.0	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)
Quantisation	mxfp4, Q4, Q8	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
Backend	Metal	BLAS + Metal, Metal
Cooldown	off	off, on
Conditioning	warmup_only	idle_reset_then_warm, runtime_native_warmup, warmup_only
Decode workload	TG128 @ 1 ctx	TG128, TG128 @ 1 ctx
Harness schema	basert-benchmark-harness/1	basert-benchmark-harness/1, computearena-measurements/1

Like-for-like pairs

Each row is a configuration present on both sides. Values are per-cell medians; ratios read Apple M4 Pro relative to Apple M5 Pro.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Llama-3.2-3B-Instruct BaseRTQ4	82.9	94.6	0.88×	938	4,297	0.22×	4 / 5
Qwen3-8B BaseRTQ4	52.5	59.7	0.88×	397	1,761	0.23×	2 / 7
Llama-3.1-8B-Instruct BaseRTQ4	43.9	48.8	0.90×	393	1,784	0.22×	4 / 4
Llama-3.2-1B-Instruct BaseRTQ4	189.2	206.3	0.92×	2,688	11,673	0.23×	4 / 3
Mistral-7B-Instruct-v0.3 BaseRTQ4	46.2	51.7	0.89×	392	1,789	0.22×	4 / 2
Qwen3-0.6B BaseRTQ4	305.2	512.0	0.60×	4,298	20,603	0.21×	2 / 3
Qwen3-0.6B BaseRTQ8	291.7	349.8	0.83×	4,816	20,366	0.24×	2 / 3
gemma-3-1b-it BaseRTQ4	222.8	281.7	0.79×	3,400	14,392	0.24×	2 / 2
gemma-4-E4B-it BaseRTQ4	68.9	82.3	0.84×	1,098	4,646	0.24×	2 / 2
gemma-4-E4B-it BaseRTQ8	44.3	51.2	0.87×	1,077	4,476	0.24×	2 / 2
gpt-oss-20b BaseRTQ4	78.9	110.5	0.71×	732	1,156	0.63×	2 / 2
Qwen3-1.7B BaseRTQ4	191.9	222.9	0.86×	1,825	7,654	0.24×	2 / 2
Qwen3-1.7B BaseRTQ8	125.3	132.4	0.95×	1,820	7,655	0.24×	2 / 2
Qwen3-4B BaseRTQ4	89.8	105.6	0.85×	734	3,378	0.22×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ4	77.9	89.9	0.87×	726	3,345	0.22×	2 / 2
Qwen3-4B-Instruct-2507 BaseRTQ8	56.1	63.5	0.88×	728	3,402	0.21×	2 / 2
Qwen3-8B BaseRTQ8	31.6	34.9	0.91×	393	1,746	0.22×	2 / 2
gemma-3-1b-it BaseRTQ8	175.4	210.3	0.83×	3,382	15,061	0.22×	2 / 1
gemma-4-E2B-it BaseRTQ4	123.9	144.6	0.86×	3,729	13,240	0.28×	2 / 1
gemma-4-E2B-it BaseRTQ8	83.8	96.0	0.87×	3,631	12,646	0.29×	2 / 1
gpt-oss-20b BaseRTQ8	73.4	100.6	0.73×	730	1,065	0.69×	2 / 1
gpt-oss-20b BaseRTmxfp4	72.5	103.6	0.70×	736	1,013	0.73×	2 / 1
Qwen3-4B BaseRTQ8	56.0	64.7	0.87×	725	3,412	0.21×	2 / 1
Qwen3-4B-Thinking-2507 BaseRTQ4	78.1	91.6	0.85×	729	3,363	0.22×	2 / 1
Qwen3-4B-Thinking-2507 BaseRTQ8	56.2	64.7	0.87×	729	3,414	0.21×	2 / 1
Qwen3.5-2B BaseRTQ4	175.6	217.7	0.81×	1,492	2,641	0.56×	2 / 1
Qwen3.5-2B BaseRTQ8	112.9	130.7	0.86×	1,475	2,638	0.56×	2 / 1
Qwen3.5-2B-Base BaseRTQ4	174.7	218.2	0.80×	1,483	2,645	0.56×	2 / 1
Qwen3.5-2B-Base BaseRTQ8	113.6	131.4	0.86×	1,479	2,642	0.56×	2 / 1

Side A · Apple M4 Pro

Top 25 of 70 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-0.6B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	401.9 TG128 @ 1 ctx	5,025 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q8 BaseRT 0.3.0Q8	Apple M4 Pro Metal	298.7 TG128 @ 1 ctx	4,845 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	284.7 TG128 @ 1 ctx	4,787 PP512	basecompute	19 Sep 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	224.9 TG128 @ 1 ctx	3,430 PP512	basecompute	19 Sep 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	220.7 TG128 @ 1 ctx	3,369 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-0.6B-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	208.6 TG128 @ 1 ctx	3,571 PP512	basecompute	19 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	204.6 TG128 @ 1 ctx	2,685 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	199.0 TG128 @ 1 ctx	2,679 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	193.1 TG128 @ 1 ctx	1,828 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	190.7 TG128 @ 1 ctx	1,822 PP512	basecompute	9 Oct 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.2.6Q4	Apple M4 Pro Metal	179.3 TG128 @ 1 ctx	2,692 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	179.1 TG128 @ 1 ctx	1,150 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	178.8 TG128 @ 1 ctx	3,337 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	176.8 TG128 @ 1 ctx	1,150 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.3.0Q4	Apple M4 Pro Metal	176.8 TG128 @ 1 ctx	2,691 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	173.9 TG128 @ 1 ctx	1,810 PP512	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	172.5 TG128 @ 1 ctx	1,815 PP512	basecompute	11 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	172.3 TG128 @ 1 ctx	1,835 PP512	basecompute	14 Oct 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.3.0Q8	Apple M4 Pro Metal	172.0 TG128 @ 1 ctx	3,428 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	172.0 TG128 @ 1 ctx	1,833 PP512	basecompute	9 Oct 2026	View Benchmark
gemma-4-E2B-it-Q4 BaseRT 0.2.6Q4	Apple M4 Pro Metal	126.0 TG128 @ 1 ctx	3,722 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.3.0Q8	Apple M4 Pro Metal	125.3 TG128 @ 1 ctx	1,819 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	125.3 TG128 @ 1 ctx	1,822 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-4-E2B-it-Q4 BaseRT 0.3.0Q4	Apple M4 Pro Metal	121.8 TG128 @ 1 ctx	3,736 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-Base-Q8 BaseRT 0.2.6Q8	Apple M4 Pro Metal	113.9 TG128 @ 1 ctx	1,149 PP512	basecompute	20 Sep 2026	View Benchmark

Side B · 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