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: 12
Like-for-like pair: 1
Chips available: 8

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

6 runs vs 6 runs · 1 like-for-like pair

Held fixedModel: Qwen3.8 27BPrefill: PP512Decode: TG128

Chip comparison

Apple M1 Max vs NVIDIA GB10

Ratios read side A relative to side B. Geometric mean over 1 like-for-like pair.

Decode: 1.41×+40.8%
Prefill: 0.07×-92.8%

Side A

Apple M1 Max

6 runs

1 contributor

Latest 9 Oct 2026

Decode · TG128: 14.6tok/s median
best 18.2 · worst 11.0
Prefill · PP512: 82tok/s median
best 143 · worst 82

Models: 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: Q4
Backends: Metal
Cooldown: off
Conditioning: warmup_only
Decode workload: TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1

Side B

NVIDIA GB10

6 runs

1 contributor

Latest 9 Oct 2026

Decode · TG128: 10.3tok/s median
best 13.1 · worst 7.5
Prefill · PP512: 1,144tok/s median
best 1,713 · worst 1,127

Models: 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: Q4
Backends: CUDA
Cooldown: off
Conditioning: warmup_only
Decode workload: TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1

What differs besides the chip

Facet	Apple M1 Max	NVIDIA GB10
Backend	Metal	CUDA

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 NVIDIA GB10.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Qwen3.8-27B BaseRTQ4	14.6	10.3	1.41×	82	1,144	0.07×	6 / 6

Side A · Apple M1 Max

Top 6 of 6 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3.8-27B-Q4-mtp BaseRT 0.2.6Q4	Apple M1 Max Metal	18.2 TG128 @ 1 ctx	82 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.8-27B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	18.2 TG128 @ 1 ctx	82 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	18.1 TG128 @ 1 ctx	143 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	11.0 TG128 @ 1 ctx	82 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.3.0Q4	Apple M1 Max Metal	11.0 TG128 @ 1 ctx	143 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	11.0 TG128 @ 1 ctx	82 PP512	basecompute	19 Sep 2026	View Benchmark

Side B · NVIDIA GB10

Top 6 of 6 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3.8-27B-Q4 BaseRT 0.3.0Q4	NVIDIA GB10 CUDA	13.1 TG128 @ 1 ctx	1,713 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q4 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	13.1 TG128 @ 1 ctx	1,131 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q4-mtp BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	13.1 TG128 @ 1 ctx	1,136 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	7.6 TG128 @ 1 ctx	1,152 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.3.0Q4	NVIDIA GB10 CUDA	7.5 TG128 @ 1 ctx	1,701 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	7.5 TG128 @ 1 ctx	1,127 PP512	basecompute	19 Sep 2026	View Benchmark

Compare

Loading community benchmarks…

Facet

Apple M1 Max

NVIDIA GB10

Backend

Metal

CUDA

Configuration

Decode A

Decode B

Ratio

Prefill A

Prefill B

Ratio

Runs A / B

Qwen3.8-27B

BaseRTQ4

14.6

10.3

1.41×

1,144

0.07×

6 / 6

Side A · Apple M1 Max

Top 6 of 6 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3.8-27B-Q4-mtp BaseRT 0.2.6Q4	Apple M1 Max Metal	18.2 TG128 @ 1 ctx	82 PP512	basecompute	20 Sep 2026	View Benchmark
Qwen3.8-27B-Q4 BaseRT 0.2.6Q4	Apple M1 Max Metal	18.2 TG128 @ 1 ctx	82 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q4 BaseRT 0.3.0Q4	Apple M1 Max Metal	18.1 TG128 @ 1 ctx	143 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	11.0 TG128 @ 1 ctx	82 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.3.0Q4	Apple M1 Max Metal	11.0 TG128 @ 1 ctx	143 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	Apple M1 Max Metal	11.0 TG128 @ 1 ctx	82 PP512	basecompute	19 Sep 2026	View Benchmark

Side B · NVIDIA GB10

Top 6 of 6 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3.8-27B-Q4 BaseRT 0.3.0Q4	NVIDIA GB10 CUDA	13.1 TG128 @ 1 ctx	1,713 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q4 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	13.1 TG128 @ 1 ctx	1,131 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q4-mtp BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	13.1 TG128 @ 1 ctx	1,136 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	7.6 TG128 @ 1 ctx	1,152 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.3.0Q4	NVIDIA GB10 CUDA	7.5 TG128 @ 1 ctx	1,701 PP512	basecompute	9 Oct 2026	View Benchmark
Qwen3.8-27B-Q8 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	7.5 TG128 @ 1 ctx	1,127 PP512	basecompute	19 Sep 2026	View Benchmark