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: 9
Like-for-like pairs: 3
Chips available: 10

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

6 runs vs 3 runs · 3 like-for-like pairs

Held fixedModel: GPT OSS 20BPrefill: PP512Decode: TG128

A side mixes quantisations. Pick a quantisation to compare the same weights.
The sides differ in conditioning, decode workload, harness schema. Ratios may reflect benchmark protocol rather than the chip.

Chip comparison

Apple M5 Pro vs Apple M1 Max

Ratios read side A relative to side B. Geometric mean over 3 like-for-like pairs.

Decode: 1.34×+33.6%
Prefill: 1.22×+21.8%

Side A

Apple M5 Pro

6 runs

1 contributor

Latest 11 Sep 2026

Decode · TG128: 102.1tok/s median
best 110.9 · worst 66.6
Prefill · PP512: 1,156tok/s median
best 1,852 · worst 1,013

Models: gpt-oss-20b, Gpt-Oss-20B
Runtimes: BaseRTllama.cpp
Versions: BaseRT 0.2.4, llama.cpp b10809 (5266f24da)
Quantisations: F16, mxfp4, Q4, Q4_K_M, Q8
Backends: BLAS + Metal, Metal
Cooldown: off
Conditioning: runtime_native_warmup, warmup_only
Decode workload: TG128
Harness schema: basert-benchmark-harness/1, computearena-measurements/1

Side B

Apple M1 Max

3 runs

1 contributor

Latest 20 Sep 2026

Decode · TG128: 76.7tok/s median
best 82.3 · worst 76.6
Prefill · PP512: 881tok/s median
best 890 · worst 880

Models: gpt-oss-20b-MXFP4, gpt-oss-20b-Q4, gpt-oss-20b-Q8
Runtimes: BaseRT
Versions: BaseRT 0.2.6
Quantisations: mxfp4, 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	Apple M5 Pro	Apple M1 Max
Model	gpt-oss-20b, Gpt-Oss-20B	gpt-oss-20b-MXFP4, gpt-oss-20b-Q4, gpt-oss-20b-Q8
Runtime	BaseRT, llama.cpp	BaseRT
Runtime version	BaseRT 0.2.4, llama.cpp b10809 (5266f24da)	BaseRT 0.2.6
Quantisation	F16, mxfp4, Q4, Q4_K_M, Q8	mxfp4, Q4, Q8
Backend	BLAS + Metal, Metal	Metal
Conditioning	runtime_native_warmup, warmup_only	warmup_only
Decode workload	TG128	TG128 @ 1 ctx
Harness schema	basert-benchmark-harness/1, computearena-measurements/1	basert-benchmark-harness/1

Like-for-like pairs

Each row is a configuration present on both sides. Values are per-cell medians; ratios read Apple M5 Pro relative to Apple M1 Max.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
gpt-oss-20b BaseRTQ4	110.5	82.3	1.34×	1,156	881	1.31×	2 / 1
gpt-oss-20b BaseRTQ8	100.6	76.7	1.31×	1,065	880	1.21×	1 / 1
gpt-oss-20b BaseRTmxfp4	103.6	76.6	1.35×	1,013	890	1.14×	1 / 1

Side A · Apple M5 Pro

Top 6 of 6 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
basecompute/gpt-oss-20b BaseRT 0.2.4Q4	Apple M5 Pro Metal	110.9 TG128	1,155 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRT 0.2.4Q4	Apple M5 Pro Metal	110.1 TG128	1,156 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRT 0.2.4mxfp4	Apple M5 Pro Metal	103.6 TG128	1,013 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gpt-oss-20b BaseRT 0.2.4Q8	Apple M5 Pro Metal	100.6 TG128	1,065 PP512	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	96.3 TG128	1,849 PP512	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cpp b10809 (5266f24da)F16	Apple M5 Pro BLAS + Metal	66.6 TG128	1,852 PP512	arki05	11 Sep 2026	View Benchmark

Side B · Apple M1 Max

Top 3 of 3 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
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
gpt-oss-20b-MXFP4 BaseRT 0.2.6mxfp4	Apple M1 Max Metal	76.6 TG128 @ 1 ctx	890 PP512	basecompute	20 Sep 2026	View Benchmark