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: 15
Like-for-like pairs: 4
Chips available: 11

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

10 runs vs 5 runs · 4 like-for-like pairs

Held fixedModel: Qwen3 0.6BPrefill: PP512Decode: TG128

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

Chip comparison

Apple M5 Pro vs Apple M5 Max

Ratios read side A relative to side B. Geometric mean over 4 like-for-like pairs.

Decode: 0.73×-27.1%
Prefill: 0.61×-39.4%

Side A

Apple M5 Pro

10 runs

2 contributors

Latest 18 Sep 2026

Decode · TG128: 357.2tok/s median
best 516.8 · worst 283.0
Prefill · PP512: 19,035tok/s median
best 20,778 · worst 14,344

Models: Qwen3-0.6B
Runtimes: BaseRTllama.cpp
Versions: BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da)
Quantisations: Q4, Q4_K_M, Q8, Q8_0
Backends: BLAS + Metal, Metal
Cooldown: off
Conditioning: runtime_native_warmup, warmup_only
Decode workload: TG128, TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1, computearena-measurements/1

Side B

Apple M5 Max

5 runs

2 contributors

Latest 18 Sep 2026

Decode · TG128: 549.5tok/s median
best 708.3 · worst 379.0
Prefill · PP512: 32,977tok/s median
best 34,136 · worst 24,365

Models: Models Qwen Qwen3 0.6B, Qwen3 0.6B Instruct, Qwen3-0.6B
Runtimes: BaseRTllama.cpp
Versions: BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10360 (48d22e295)
Quantisations: Q4, Q4_K_M, Q8, Q8_0
Backends: BLAS + Metal, Metal
Cooldown: off
Conditioning: runtime_native_warmup, warmup_only
Decode workload: TG128
Harness schema: basert-benchmark-harness/1, computearena-measurements/1

What differs besides the chip

Facet	Apple M5 Pro	Apple M5 Max
Model	Qwen3-0.6B	Models Qwen Qwen3 0.6B, Qwen3 0.6B Instruct, Qwen3-0.6B
Runtime version	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da)	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10360 (48d22e295)
Decode workload	TG128, TG128 @ 1 ctx	TG128

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 M5 Max.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Qwen3-0.6B BaseRTQ4	512.0	703.4	0.73×	20,603	33,557	0.61×	3 / 2
Qwen3-0.6B BaseRTQ8	349.8	549.5	0.64×	20,366	33,088	0.62×	3 / 1
Qwen3-0.6B llama.cppQ4_K_M	358.1	439.1	0.82×	14,509	24,365	0.60×	3 / 1
Qwen3-0.6B llama.cppQ8_0	283.0	379.0	0.75×	14,942	24,983	0.60×	1 / 1

Side A · Apple M5 Pro

Top 10 of 10 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
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
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

Side B · Apple M5 Max

Top 5 of 5 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
basecompute/Qwen3-0.6B BaseRT 0.2.4Q4	Apple M5 Max Metal	708.3 TG128	34,136 PP512	basecompute	10 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.5Q4	Apple M5 Max Metal	698.5 TG128	32,977 PP512	lukas	18 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRT 0.2.4Q8	Apple M5 Max Metal	549.5 TG128	33,088 PP512	basecompute	10 Sep 2026	View Benchmark
Models Qwen Qwen3 0.6B llama.cpp b10360 (48d22e295)Q4_K_M	Apple M5 Max BLAS + Metal	439.1 TG128	24,365 PP512	basecompute	10 Sep 2026	View Benchmark
Qwen3 0.6B Instruct llama.cpp b10360 (48d22e295)Q8_0	Apple M5 Max BLAS + Metal	379.0 TG128	24,983 PP512	basecompute	10 Sep 2026	View Benchmark