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: 187
Like-for-like pairs: 42
Chips available: 16

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

58 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 M3 Ultra vs Apple M5 Pro

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

Decode: 1.57×+56.5%
Prefill: 0.81×-18.9%

Side A

Apple M3 Ultra

58 runs

1 contributor

Latest 20 Sep 2026

Decode · TG128: 118.3tok/s median
best 501.7 · worst 22.1
Prefill · PP512: 2,292tok/s median
best 12,830 · worst 280

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-120b-MXFP4, 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, Qwen3.5-122B-A10B-Q4, 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 M3 Ultra	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-120b-MXFP4, 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, Qwen3.5-122B-A10B-Q4, 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 M3 Ultra relative to Apple M5 Pro.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Qwen3-8B BaseRTQ4	113.6	59.7	1.90×	1,357	1,761	0.77×	1 / 7
Llama-3.2-3B-Instruct BaseRTQ4	174.9	94.6	1.85×	3,278	4,297	0.76×	2 / 5
Llama-3.1-8B-Instruct BaseRTQ4	99.9	48.8	2.05×	1,415	1,784	0.79×	2 / 4
Llama-3.2-1B-Instruct BaseRTQ4	377.7	206.3	1.83×	9,061	11,673	0.78×	2 / 3
Mistral-7B-Instruct-v0.3 BaseRTQ4	104.1	51.7	2.01×	1,414	1,789	0.79×	2 / 2
Muse-Glimmer-30B BaseRTpassthrough_gguf	29.2	15.7	1.86×	402	480	0.84×	2 / 2
Qwen3-0.6B BaseRTQ4	501.7	512.0	0.98×	12,830	20,603	0.62×	1 / 3
Qwen3-0.6B BaseRTQ8	440.2	349.8	1.26×	12,494	20,366	0.61×	1 / 3
Qwen3.8-27B BaseRTQ4	30.0	13.5	2.22×	281	341	0.82×	2 / 2
gemma-3-1b-it BaseRTQ4	328.0	281.7	1.16×	9,903	14,392	0.69×	1 / 2
gemma-4-E4B-it BaseRTQ4	94.6	82.3	1.15×	3,610	4,646	0.78×	1 / 2
gemma-4-E4B-it BaseRTQ8	75.4	51.2	1.47×	3,499	4,476	0.78×	1 / 2
gpt-oss-20b BaseRTQ4	185.1	110.5	1.67×	2,554	1,156	2.21×	1 / 2
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ8	102.0	66.0	1.54×	2,313	1,748	1.32×	2 / 1
Qwen3-1.7B BaseRTQ4	307.4	222.9	1.38×	5,420	7,654	0.71×	1 / 2
Qwen3-1.7B BaseRTQ8	238.6	132.4	1.80×	5,698	7,655	0.74×	1 / 2
Qwen3-30B-A3B-Instruct-2507 BaseRTQ4	137.1	98.1	1.40×	2,287	3,493	0.65×	1 / 2
Qwen3-30B-A3B-Thinking-2507 BaseRTQ8	95.9	65.1	1.47×	2,340	3,692	0.63×	2 / 1
Qwen3-4B BaseRTQ4	165.7	105.6	1.57×	2,461	3,378	0.73×	1 / 2
Qwen3-4B-Instruct-2507 BaseRTQ4	153.7	89.9	1.71×	2,529	3,345	0.76×	1 / 2
Qwen3-4B-Instruct-2507 BaseRTQ8	118.3	63.5	1.86×	2,557	3,402	0.75×	1 / 2
Qwen3-8B BaseRTQ8	72.5	34.9	2.08×	1,338	1,746	0.77×	1 / 2
gemma-3-1b-it BaseRTQ8	257.8	210.3	1.23×	9,953	15,061	0.66×	1 / 1
gemma-4-26B-A4B-it BaseRTQ4	81.5	51.7	1.58×	2,422	2,047	1.18×	1 / 1
gemma-4-26B-A4B-it BaseRTQ8	75.3	51.4	1.46×	2,258	3,253	0.69×	1 / 1
gemma-4-E2B-it BaseRTQ4	137.4	144.6	0.95×	8,996	13,240	0.68×	1 / 1
gemma-4-E2B-it BaseRTQ8	116.6	96.0	1.21×	8,610	12,646	0.68×	1 / 1
gpt-oss-20b BaseRTQ8	175.8	100.6	1.75×	2,627	1,065	2.47×	1 / 1
gpt-oss-20b BaseRTmxfp4	163.9	103.6	1.58×	2,590	1,013	2.56×	1 / 1
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 BaseRTQ4	171.6	100.1	1.71×	2,295	2,499	0.92×	1 / 1
Qwen3-30B-A3B-Thinking-2507 BaseRTQ4	135.3	104.4	1.30×	2,416	3,694	0.65×	1 / 1
Qwen3-4B BaseRTQ8	116.8	64.7	1.81×	2,441	3,412	0.72×	1 / 1
Qwen3-4B-Thinking-2507 BaseRTQ4	155.6	91.6	1.70×	2,582	3,363	0.77×	1 / 1
Qwen3-4B-Thinking-2507 BaseRTQ8	118.2	64.7	1.83×	2,559	3,414	0.75×	1 / 1
Qwen3.5-2B BaseRTQ4	306.7	217.7	1.41×	1,759	2,641	0.67×	1 / 1
Qwen3.5-2B BaseRTQ8	222.9	130.7	1.70×	1,756	2,638	0.67×	1 / 1
Qwen3.5-2B-Base BaseRTQ4	293.8	218.2	1.35×	1,756	2,645	0.66×	1 / 1
Qwen3.5-2B-Base BaseRTQ8	222.4	131.4	1.69×	1,696	2,642	0.64×	1 / 1
Qwen3.5-35B-A3B BaseRTQ4	133.0	113.4	1.17×	947	1,304	0.73×	1 / 1
Qwen3.6-27B BaseRTQ4	36.8	16.1	2.28×	281	364	0.77×	1 / 1
Qwen3.6-27B BaseRTQ8	22.1	10.6	2.10×	280	355	0.79×	1 / 1
Qwen3.6-35B-A3B BaseRTQ4	133.0	113.2	1.17×	922	1,275	0.72×	1 / 1

Side A · Apple M3 Ultra

Top 25 of 58 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-0.6B-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	501.7 TG128 @ 1 ctx	12,830 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3-0.6B-Q8 BaseRT 0.2.6Q8	Apple M3 Ultra Metal	440.2 TG128 @ 1 ctx	12,494 PP512	basecompute	19 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	410.1 TG128 @ 1 ctx	9,066 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-1B-Instruct-Q8 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	345.2 TG128 @ 1 ctx	9,055 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	328.0 TG128 @ 1 ctx	9,903 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	307.4 TG128 @ 1 ctx	5,420 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	306.7 TG128 @ 1 ctx	1,759 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	293.8 TG128 @ 1 ctx	1,756 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-3-1b-it-Q8 BaseRT 0.2.6Q8	Apple M3 Ultra Metal	257.8 TG128 @ 1 ctx	9,953 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-1.7B-Q8 BaseRT 0.2.6Q8	Apple M3 Ultra Metal	238.6 TG128 @ 1 ctx	5,698 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Q8 BaseRT 0.2.6Q8	Apple M3 Ultra Metal	222.9 TG128 @ 1 ctx	1,756 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-Base-Q8 BaseRT 0.2.6Q8	Apple M3 Ultra Metal	222.4 TG128 @ 1 ctx	1,696 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-3B-Instruct-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	195.4 TG128 @ 1 ctx	3,241 PP512	basecompute	20 Sep 2026	View Benchmark
gpt-oss-20b-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	185.1 TG128 @ 1 ctx	2,554 PP512	basecompute	20 Sep 2026	View Benchmark
gpt-oss-20b-Q8 BaseRT 0.2.6Q8	Apple M3 Ultra Metal	175.8 TG128 @ 1 ctx	2,627 PP512	basecompute	20 Sep 2026	View Benchmark
NVIDIA-Nemotron-3-Nano-30B-A3B-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	171.6 TG128 @ 1 ctx	2,295 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	165.7 TG128 @ 1 ctx	2,461 PP512	basecompute	20 Sep 2026	View Benchmark
gpt-oss-20b-MXFP4 BaseRT 0.2.6mxfp4	Apple M3 Ultra Metal	163.9 TG128 @ 1 ctx	2,590 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Thinking-2507-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	155.6 TG128 @ 1 ctx	2,582 PP512	basecompute	20 Sep 2026	View Benchmark
Llama-3.2-3B-Instruct-Q8 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	154.4 TG128 @ 1 ctx	3,316 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	153.7 TG128 @ 1 ctx	2,529 PP512	basecompute	20 Sep 2026	View Benchmark
gemma-4-E2B-it-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	137.4 TG128 @ 1 ctx	8,996 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	137.1 TG128 @ 1 ctx	2,287 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3-30B-A3B-Thinking-2507-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	135.3 TG128 @ 1 ctx	2,416 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-Q4 BaseRT 0.2.6Q4	Apple M3 Ultra Metal	133.0 TG128 @ 1 ctx	922 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