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: 41
Like-for-like pairs: 8
Chips available: 9

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

27 runs vs 14 runs · 8 like-for-like pairs

Held fixedModel: Qwen3 8BPrefill: 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 AMD Radeon RX 7900 XT

Ratios read side A relative to side B. Geometric mean over 8 like-for-like pairs.

Decode: 0.54×-46.5%
Prefill: 0.48×-51.9%

Side A

Apple M5 Pro

27 runs

2 contributors

Latest 18 Sep 2026

Decode · TG128: 55.0tok/s median
best 81.8 · worst 18.9
Prefill · PP512: 1,535tok/s median
best 1,786 · worst 1,345

Models: Qwen3-8B, Qwen3-8B-base-q2, Qwen3-8B-base-q3, Qwen3-8B-base-q5, Qwen3-8B-base-q6
Runtimes: BaseRTllama.cpp
Versions: BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da)
Quantisations: BF16, Q2, Q2_K, Q3, Q3_K_M, Q4, Q4_1, Q4_K_M, Q5, Q5_K_M, Q6, Q6_K, 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

AMD Radeon RX 7900 XT

14 runs

1 contributor

Latest 11 Sep 2026

Decode · TG128: 89.5tok/s median
best 112.3 · worst 43.5
Prefill · PP512: 2,898tok/s median
best 3,241 · worst 2,798

Models: Qwen3-8B
Runtimes: llama.cpp
Versions: llama.cpp b10809 (5266f24da)
Quantisations: BF16, Q2_K, Q3_K_M, Q4_1, Q4_K_M, Q5_K_M, Q6_K, Q8_0
Backends: ROCm
Cooldown: off
Conditioning: runtime_native_warmup
Decode workload: TG128
Harness schema: computearena-measurements/1

What differs besides the chip

Facet	Apple M5 Pro	AMD Radeon RX 7900 XT
Model	Qwen3-8B, Qwen3-8B-base-q2, Qwen3-8B-base-q3, Qwen3-8B-base-q5, Qwen3-8B-base-q6	Qwen3-8B
Runtime	BaseRT, llama.cpp	llama.cpp
Runtime version	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da)	llama.cpp b10809 (5266f24da)
Quantisation	BF16, Q2, Q2_K, Q3, Q3_K_M, Q4, Q4_1, Q4_K_M, Q5, Q5_K_M, Q6, Q6_K, Q8, Q8_0	BF16, Q2_K, Q3_K_M, Q4_1, Q4_K_M, Q5_K_M, Q6_K, Q8_0
Backend	BLAS + Metal, Metal	ROCm
Conditioning	runtime_native_warmup, warmup_only	runtime_native_warmup
Decode workload	TG128, TG128 @ 1 ctx	TG128
Harness schema	basert-benchmark-harness/1, computearena-measurements/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 M5 Pro relative to AMD Radeon RX 7900 XT.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Qwen3-8B llama.cppQ2_K	71.2	108.9	0.65×	1,471	2,816	0.52×	2 / 2
Qwen3-8B llama.cppQ3_K_M	61.2	91.6	0.67×	1,416	2,887	0.49×	2 / 2
Qwen3-8B llama.cppQ4_K_M	54.3	93.5	0.58×	1,399	3,093	0.45×	2 / 2
Qwen3-8B llama.cppQ5_K_M	47.7	87.2	0.55×	1,349	2,853	0.47×	2 / 2
Qwen3-8B llama.cppQ6_K	41.0	82.0	0.50×	1,414	2,863	0.49×	2 / 2
Qwen3-8B llama.cppQ8_0	31.8	69.1	0.46×	1,460	3,224	0.45×	2 / 2
Qwen3-8B llama.cppBF16	18.9	43.5	0.43×	1,376	3,133	0.44×	1 / 1
Qwen3-8B llama.cppQ4_1	51.9	107.3	0.48×	1,535	2,894	0.53×	1 / 1

Side A · Apple M5 Pro

Top 25 of 27 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-8B-base-q2 BaseRT 0.2.4Q2	Apple M5 Pro Metal	81.8 TG128	1,786 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q2_K	Apple M5 Pro BLAS + Metal	72.8 TG128	1,477 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q2_K	Apple M5 Pro BLAS + Metal	69.6 TG128	1,465 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B-base-q3 BaseRT 0.2.4Q3	Apple M5 Pro Metal	62.0 TG128	1,748 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q3_K_M	Apple M5 Pro BLAS + Metal	61.5 TG128	1,418 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q3_K_M	Apple M5 Pro BLAS + Metal	60.9 TG128	1,414 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q4	Apple M5 Pro Metal	60.7 TG128	1,755 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q4	Apple M5 Pro Metal	60.6 TG128	1,763 PP512	isu	10 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q4	Apple M5 Pro Metal	60.5 TG128	1,763 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.5Q4	Apple M5 Pro Metal	59.7 TG128 @ 1 ctx	1,762 PP512	isu	18 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q4	Apple M5 Pro Metal	59.7 TG128	1,761 PP512	isu	11 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q4	Apple M5 Pro Metal	58.2 TG128	1,758 PP512	isu	11 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q4	Apple M5 Pro Metal	56.9 TG128	1,707 PP512	isu	10 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	55.0 TG128	1,401 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	53.6 TG128	1,396 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q4_1	Apple M5 Pro BLAS + Metal	51.9 TG128	1,535 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B-base-q5 BaseRT 0.2.4Q5	Apple M5 Pro Metal	48.4 TG128	1,730 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q5_K_M	Apple M5 Pro BLAS + Metal	47.9 TG128	1,345 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q5_K_M	Apple M5 Pro BLAS + Metal	47.6 TG128	1,353 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q6_K	Apple M5 Pro BLAS + Metal	42.6 TG128	1,409 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B-base-q6 BaseRT 0.2.4Q6	Apple M5 Pro Metal	42.1 TG128	1,723 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q6_K	Apple M5 Pro BLAS + Metal	39.4 TG128	1,419 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q8	Apple M5 Pro Metal	35.2 TG128	1,748 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-8B BaseRT 0.2.4Q8	Apple M5 Pro Metal	34.5 TG128	1,744 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q8_0	Apple M5 Pro BLAS + Metal	34.4 TG128	1,473 PP512	arki05	11 Sep 2026	View Benchmark

Side B · AMD Radeon RX 7900 XT

Top 14 of 14 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-8B llama.cpp b10809 (5266f24da)Q2_K	AMD Radeon RX 7900 XT ROCm	112.3 TG128	2,798 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q4_1	AMD Radeon RX 7900 XT ROCm	107.3 TG128	2,894 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q2_K	AMD Radeon RX 7900 XT ROCm	105.5 TG128	2,834 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	93.7 TG128	3,110 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	93.2 TG128	3,076 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q3_K_M	AMD Radeon RX 7900 XT ROCm	91.6 TG128	2,864 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q3_K_M	AMD Radeon RX 7900 XT ROCm	91.6 TG128	2,911 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q5_K_M	AMD Radeon RX 7900 XT ROCm	87.5 TG128	2,837 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q5_K_M	AMD Radeon RX 7900 XT ROCm	86.8 TG128	2,869 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q6_K	AMD Radeon RX 7900 XT ROCm	84.0 TG128	2,823 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q6_K	AMD Radeon RX 7900 XT ROCm	80.1 TG128	2,903 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q8_0	AMD Radeon RX 7900 XT ROCm	74.2 TG128	3,241 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)Q8_0	AMD Radeon RX 7900 XT ROCm	64.0 TG128	3,207 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-8B llama.cpp b10809 (5266f24da)BF16	AMD Radeon RX 7900 XT ROCm	43.5 TG128	3,133 PP512	arki05	11 Sep 2026	View Benchmark