Compare

Loading community benchmarks…

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: 185
Like-for-like pairs: 42
Chips available: 16

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

56 runs vs 129 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 M1 Max vs Apple M5 Pro

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

Decode: 0.89×-11.1%
Prefill: 0.28×-72.5%

Side A

Apple M1 Max

56 runs

1 contributor

Latest 20 Sep 2026

Decode · TG128: 73.3tok/s median
best 242.1 · worst 11.0
Prefill · PP512: 874tok/s median
best 4,521 · 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
Quantisations: mxfp4, passthrough_gguf, 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 M1 Max	Apple M5 Pro
Model	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	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 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)
Quantisation	mxfp4, passthrough_gguf, 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 M1 Max relative to Apple M5 Pro.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Qwen3-8B BaseRTQ4	60.2	59.7	1.01×	507	1,761	0.29×	1 / 7
Llama-3.2-3B-Instruct BaseRTQ4	99.5	94.6	1.05×	1,235	4,297	0.29×	2 / 5
Llama-3.1-8B-Instruct BaseRTQ4	51.2	48.8	1.05×	509	1,784	0.29×	2 / 4
Llama-3.2-1B-Instruct BaseRTQ4	235.8	206.3	1.14×	3,353	11,673	0.29×	2 / 3
Qwen3.8-27B BaseRTQ4	11.0	13.5	0.82×	82	341	0.24×	3 / 2
Mistral-7B-Instruct-v0.3 BaseRTQ4	53.5	51.7	1.03×	510	1,789	0.28×	2 / 2
Muse-Glimmer-30B BaseRTpassthrough_gguf	15.8	15.7	1.01×	138	480	0.29×	2 / 2
Qwen3-0.6B BaseRTQ4	100.8	512.0	0.20×	1,851	20,603	0.09×	1 / 3
Qwen3-0.6B BaseRTQ8	74.3	349.8	0.21×	2,225	20,366	0.11×	1 / 3
gemma-3-1b-it BaseRTQ4	220.0	281.7	0.78×	4,102	14,392	0.29×	1 / 2
gemma-4-E4B-it BaseRTQ4	75.9	82.3	0.92×	1,394	4,646	0.30×	1 / 2
gemma-4-E4B-it BaseRTQ8	52.0	51.2	1.02×	1,368	4,476	0.31×	1 / 2
gpt-oss-20b BaseRTQ4	82.3	110.5	0.74×	881	1,156	0.76×	1 / 2
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ8	60.8	66.0	0.92×	858	1,748	0.49×	2 / 1
Qwen3-1.7B BaseRTQ4	219.7	222.9	0.99×	2,244	7,654	0.29×	1 / 2
Qwen3-1.7B BaseRTQ8	153.9	132.4	1.16×	2,223	7,655	0.29×	1 / 2
Qwen3-30B-A3B-Instruct-2507 BaseRTQ4	87.7	98.1	0.89×	901	3,493	0.26×	1 / 2
Qwen3-30B-A3B-Thinking-2507 BaseRTQ8	64.1	65.1	0.99×	894	3,692	0.24×	2 / 1
Qwen3-4B BaseRTQ4	101.9	105.6	0.96×	927	3,378	0.27×	1 / 2
Qwen3-4B-Instruct-2507 BaseRTQ4	91.3	89.9	1.02×	922	3,345	0.28×	1 / 2
Qwen3-4B-Instruct-2507 BaseRTQ8	72.1	63.5	1.13×	925	3,402	0.27×	1 / 2
Qwen3-8B BaseRTQ8	38.1	34.9	1.09×	500	1,746	0.29×	1 / 2
gemma-3-1b-it BaseRTQ8	170.0	210.3	0.81×	4,120	15,061	0.27×	1 / 1
gemma-4-26B-A4B-it BaseRTQ4	51.5	51.7	1.00×	871	2,047	0.43×	1 / 1
gemma-4-26B-A4B-it BaseRTQ8	45.5	51.4	0.88×	877	3,253	0.27×	1 / 1
gemma-4-E2B-it BaseRTQ4	120.8	144.6	0.84×	4,521	13,240	0.34×	1 / 1
gemma-4-E2B-it BaseRTQ8	91.1	96.0	0.95×	4,442	12,646	0.35×	1 / 1
gpt-oss-20b BaseRTQ8	76.7	100.6	0.76×	880	1,065	0.83×	1 / 1
gpt-oss-20b BaseRTmxfp4	76.6	103.6	0.74×	890	1,013	0.88×	1 / 1
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ4	110.3	100.1	1.10×	870	2,499	0.35×	1 / 1
Qwen3-30B-A3B-Thinking-2507 BaseRTQ4	87.2	104.4	0.84×	901	3,694	0.24×	1 / 1
Qwen3-4B BaseRTQ8	71.3	64.7	1.10×	920	3,412	0.27×	1 / 1
Qwen3-4B-Thinking-2507 BaseRTQ4	93.2	91.6	1.02×	921	3,363	0.27×	1 / 1
Qwen3-4B-Thinking-2507 BaseRTQ8	71.5	64.7	1.10×	925	3,414	0.27×	1 / 1
Qwen3.5-2B BaseRTQ4	192.9	217.7	0.89×	429	2,641	0.16×	1 / 1
Qwen3.5-2B BaseRTQ8	141.5	130.7	1.08×	400	2,638	0.15×	1 / 1
Qwen3.5-2B-Base BaseRTQ4	190.0	218.2	0.87×	439	2,645	0.17×	1 / 1
Qwen3.5-2B-Base BaseRTQ8	140.7	131.4	1.07×	438	2,642	0.17×	1 / 1
Qwen3.5-35B-A3B BaseRTQ4	93.7	113.4	0.83×	280	1,304	0.21×	1 / 1
Qwen3.6-27B BaseRTQ4	17.9	16.1	1.11×	80	364	0.22×	1 / 1
Qwen3.6-27B BaseRTQ8	11.0	10.6	1.04×	83	355	0.23×	1 / 1
Qwen3.6-35B-A3B BaseRTQ4	94.2	113.2	0.83×	278	1,275	0.22×	1 / 1

Side A · Apple M1 Max

Top 25 of 56 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
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-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	229.4 TG128 @ 1 ctx	3,372 PP512	basecompute	20 Sep 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
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
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
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
Qwen3.5-2B-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
gemma-4-E2B-it-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	120.8 TG128 @ 1 ctx	4,521 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-3B-Instruct-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	110.7 TG128 @ 1 ctx	1,229 PP512	basecompute	20 Sep 2026	View Benchmark
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	110.3 TG128 @ 1 ctx	870 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	101.9 TG128 @ 1 ctx	927 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-0.6B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	100.8 TG128 @ 1 ctx	1,851 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	94.2 TG128 @ 1 ctx	278 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-35B-A3B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	93.7 TG128 @ 1 ctx	280 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3-4B-Thinking-2507-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	93.2 TG128 @ 1 ctx	921 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	91.3 TG128 @ 1 ctx	922 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-4-E2B-it-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	91.1 TG128 @ 1 ctx	4,442 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-3B-Instruct-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	88.4 TG128 @ 1 ctx	1,240 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	87.7 TG128 @ 1 ctx	901 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	87.2 TG128 @ 1 ctx	901 PP512	basecompute	20 Sep 2026	View Benchmark
gpt-oss-20b-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	82.3 TG128 @ 1 ctx	881 PP512	basecompute	20 Sep 2026	View Benchmark
gpt-oss-20b-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	76.7 TG128 @ 1 ctx	880 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