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: 5
Like-for-like pair: 1
Chips available: 7

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

3 runs vs 2 runs · 1 like-for-like pair

Held fixedModel: Qwen3.5 2BPrefill: PP512Decode: TG128

Apple M1 Max has only 2 matching runs. Treat its figures as indicative.
A side mixes quantisations. Pick a quantisation to compare the same weights.

Chip comparison

NVIDIA GB10 vs Apple M1 Max

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

Decode: 0.79×-21.5%
Prefill: 15.73×+1473%

Side A

NVIDIA GB10

3 runs

1 contributor

Latest 19 Sep 2026

Decode · TG128: 151.5tok/s median
best 181.6 · worst 113.5
Prefill · PP512: 6,754tok/s median
best 6,837 · worst 4,185

Models: Qwen3.5-2B-cuda-q4mix, Qwen3.5-2B-cuda-q8, Qwen3.5-2B-Q4
Runtimes: BaseRT
Versions: BaseRT 0.2.6
Quantisations: Q4
Backends: CUDA
Cooldown: off
Conditioning: warmup_only
Decode workload: TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1

Side B

Apple M1 Max

2 runs

1 contributor

Latest 20 Sep 2026

Decode · TG128: 167.2tok/s median
best 192.9 · worst 141.5
Prefill · PP512: 414tok/s median
best 429 · worst 400

Models: Qwen3.5-2B-Q4, Qwen3.5-2B-Q8
Runtimes: BaseRT
Versions: BaseRT 0.2.6
Quantisations: 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	NVIDIA GB10	Apple M1 Max
Model	Qwen3.5-2B-cuda-q4mix, Qwen3.5-2B-cuda-q8, Qwen3.5-2B-Q4	Qwen3.5-2B-Q4, Qwen3.5-2B-Q8
Quantisation	Q4	Q4, Q8
Backend	CUDA	Metal

Like-for-like pairs

Each row is a configuration present on both sides. Values are per-cell medians; ratios read NVIDIA GB10 relative to Apple M1 Max.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Qwen3.5-2B BaseRTQ4	151.5	192.9	0.79×	6,754	429	15.73×	3 / 1

Side A · NVIDIA GB10

Top 3 of 3 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3.5-2B-Q4 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	181.6 TG128 @ 1 ctx	4,185 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-2B-cuda-q4mix BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	151.5 TG128 @ 1 ctx	6,837 PP512	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-2B-cuda-q8 BaseRT 0.2.6Q4	NVIDIA GB10 CUDA	113.5 TG128 @ 1 ctx	6,754 PP512	basecompute	19 Sep 2026	View Benchmark

Side B · Apple M1 Max

Top 2 of 2 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
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-Q8 BaseRT 0.2.6Q8	Apple M1 Max Metal	141.5 TG128 @ 1 ctx	400 PP512	basecompute	20 Sep 2026	View Benchmark