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: 170
Like-for-like pairs: 28
Chips available: 16

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

41 runs vs 129 runs · 28 like-for-like pairs

Held fixedPrefill: PP512Decode: TG128

These figures mix different models. Pick a model for a like-for-like comparison.
A side mixes quantisations. Pick a quantisation to compare the same weights.
The sides differ in cooldown, conditioning, decode workload, harness schema. Ratios may reflect benchmark protocol rather than the chip.

Chip comparison

AMD Radeon RX 7900 XT vs Apple M5 Pro

Ratios read side A relative to side B. Geometric mean over 28 like-for-like pairs.

Decode: 1.69×+68.9%
Prefill: 1.93×+93.3%

Side A

AMD Radeon RX 7900 XT

41 runs

1 contributor

Latest 11 Sep 2026

Decode · TG128: 105.5tok/s median
best 368.6 · worst 29.3
Prefill · PP512: 3,133tok/s median
best 24,691 · worst 807

Models: Gemma-4-E4B-It, Gpt-Oss-20B, Llama 3.2 3B Instruct, Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Qwen3-0.6B, Qwen3-30B-A3B-Instruct-2507, Qwen3-4B-Instruct-2507, Qwen3-8B, Qwen3.6-27B, Qwen3.6-35B-A3B
Runtimes: llama.cpp
Versions: llama.cpp b10809 (5266f24da)
Quantisations: BF16, F16, Q2_K, Q3_K_M, Q4_0, 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

Side B

Apple M5 Pro

129 runs

2 contributors

Latest 18 Sep 2026

Decode · TG128: 72.8tok/s median
best 2,068.0 · worst 10.6
Prefill · PP512: 1,852tok/s median
best 190,107 · worst 327

Models: gemma-3-1b-it, gemma-4-26B-A4B-it, gemma-4-E2B-it, gemma-4-E4B-it, Gemma-4-E4B-It, gpt-oss-20b, Gpt-Oss-20B, Llama 3.2 3B Instruct, Llama-3.1-8B-Instruct, Llama-3.2-1B-Instruct, Llama-3.2-3B-Instruct, Mistral-7B-Instruct-v0.3, Muse-Glimmer-30B, NVIDIA-Nemotron-3-Nano-30B-A3B, Qwen3-0.6B, Qwen3-1.7B, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Thinking-2507, Qwen3-4B, Qwen3-4B-Instruct-2507, Qwen3-4B-Thinking-2507, Qwen3-8B, Qwen3-8B-base-q2, Qwen3-8B-base-q3, Qwen3-8B-base-q5, Qwen3-8B-base-q6, Qwen3.5-2B, Qwen3.5-2B-Base, Qwen3.5-35B-A3B, Qwen3.6-27B, Qwen3.6-35B-A3B, Qwen3.8-27B, Tinystories Lay8 Hs512 Hd8 33M, tinystories-lay8-hs512-hd8-33M
Runtimes: BaseRTllama.cpp
Versions: BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)
Quantisations: BF16, F16, mxfp4, passthrough_gguf, Q2, Q2_K, Q3, Q3_K_M, Q4, Q4_0, Q4_1, Q4_K_M, Q5, Q5_K_M, Q6, Q6_K, Q8, Q8_0
Backends: BLAS + Metal, Metal
Cooldown: off, on
Conditioning: idle_reset_then_warm, runtime_native_warmup, warmup_only
Decode workload: TG128, TG128 @ 1 ctx
Harness schema: basert-benchmark-harness/1, computearena-measurements/1

What differs besides the chip

Facet	AMD Radeon RX 7900 XT	Apple M5 Pro
Model	Gemma-4-E4B-It, Gpt-Oss-20B, Llama 3.2 3B Instruct, Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Qwen3-0.6B, Qwen3-30B-A3B-Instruct-2507, Qwen3-4B-Instruct-2507, Qwen3-8B, Qwen3.6-27B, Qwen3.6-35B-A3B	gemma-3-1b-it, gemma-4-26B-A4B-it, gemma-4-E2B-it, gemma-4-E4B-it, Gemma-4-E4B-It, gpt-oss-20b, Gpt-Oss-20B, Llama 3.2 3B Instruct, Llama-3.1-8B-Instruct, Llama-3.2-1B-Instruct, Llama-3.2-3B-Instruct, Mistral-7B-Instruct-v0.3, Muse-Glimmer-30B, NVIDIA-Nemotron-3-Nano-30B-A3B, Qwen3-0.6B, Qwen3-1.7B, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Thinking-2507, Qwen3-4B, Qwen3-4B-Instruct-2507, Qwen3-4B-Thinking-2507, Qwen3-8B, Qwen3-8B-base-q2, Qwen3-8B-base-q3, Qwen3-8B-base-q5, Qwen3-8B-base-q6, Qwen3.5-2B, Qwen3.5-2B-Base, Qwen3.5-35B-A3B, Qwen3.6-27B, Qwen3.6-35B-A3B, Qwen3.8-27B, Tinystories Lay8 Hs512 Hd8 33M, tinystories-lay8-hs512-hd8-33M
Runtime	llama.cpp	BaseRT, llama.cpp
Runtime version	llama.cpp b10809 (5266f24da)	BaseRT 0.2.4, BaseRT 0.2.5, llama.cpp b10809 (5266f24da), llama.cpp b9960 (a935fbffe)
Quantisation	BF16, F16, Q2_K, Q3_K_M, Q4_0, Q4_1, Q4_K_M, Q5_K_M, Q6_K, Q8_0	BF16, F16, mxfp4, passthrough_gguf, Q2, Q2_K, Q3, Q3_K_M, Q4, Q4_0, Q4_1, Q4_K_M, Q5, Q5_K_M, Q6, Q6_K, Q8, Q8_0
Backend	ROCm	BLAS + Metal, Metal
Cooldown	off	off, on
Conditioning	runtime_native_warmup	idle_reset_then_warm, runtime_native_warmup, warmup_only
Decode workload	TG128	TG128, TG128 @ 1 ctx
Harness schema	computearena-measurements/1	basert-benchmark-harness/1, computearena-measurements/1

Like-for-like pairs

Each row is a configuration present on both sides. Values are per-cell medians; ratios read AMD Radeon RX 7900 XT relative to Apple M5 Pro.

Configuration	Decode A	Decode B	Ratio	Prefill A	Prefill B	Ratio	Runs A / B
Qwen3-0.6B llama.cppQ4_K_M	368.2	358.1	1.03×	23,845	14,509	1.64×	2 / 3
gemma-4-E4B-it llama.cppQ4_K_M	110.2	70.7	1.56×	4,406	2,249	1.96×	2 / 2
Llama-3.1-8B-Instruct llama.cppQ4_K_M	97.3	55.5	1.75×	3,161	1,423	2.22×	2 / 2
Llama-3.2-3B-Instruct llama.cppQ4_K_M	172.0	116.5	1.48×	6,906	3,316	2.08×	2 / 2
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M	128.5	95.1	1.35×	2,741	1,838	1.49×	2 / 2
Qwen3-4B-Instruct-2507 llama.cppQ4_K_M	147.4	93.5	1.58×	5,350	2,567	2.08×	2 / 2
Qwen3.6-27B llama.cppQ4_K_M	29.6	14.9	1.99×	841	375	2.24×	2 / 2
Qwen3-8B llama.cppQ2_K	108.9	71.2	1.53×	2,816	1,471	1.91×	2 / 2
Qwen3-8B llama.cppQ3_K_M	91.6	61.2	1.50×	2,887	1,416	2.04×	2 / 2
Qwen3-8B llama.cppQ4_K_M	93.5	54.3	1.72×	3,093	1,399	2.21×	2 / 2
Qwen3-8B llama.cppQ5_K_M	87.2	47.7	1.83×	2,853	1,349	2.11×	2 / 2
Qwen3-8B llama.cppQ6_K	82.0	41.0	2.00×	2,863	1,414	2.02×	2 / 2
Qwen3-8B llama.cppQ8_0	69.1	31.8	2.17×	3,224	1,460	2.21×	2 / 2
gemma-4-E4B-it llama.cppQ8_0	84.3	47.9	1.76×	4,564	2,346	1.95×	1 / 1
gpt-oss-20b llama.cppF16	128.8	66.6	1.93×	3,604	1,852	1.95×	1 / 1
gpt-oss-20b llama.cppQ4_K_M	160.1	96.3	1.66×	3,502	1,849	1.89×	1 / 1
Llama-3.1-8B-Instruct llama.cppQ4_0	117.4	58.7	2.00×	3,233	1,538	2.10×	1 / 1
Llama-3.1-8B-Instruct llama.cppQ6_K	87.4	43.4	2.02×	2,851	1,421	2.01×	1 / 1
Llama-3.1-8B-Instruct llama.cppQ8_0	66.2	29.6	2.24×	3,292	1,465	2.25×	1 / 1
Llama-3.2-3B-Instruct llama.cppQ8_0	142.3	76.6	1.86×	7,210	3,516	2.05×	1 / 1
Qwen3-0.6B llama.cppQ8_0	313.7	283.0	1.11×	24,691	14,942	1.65×	1 / 1
Qwen3-30B-A3B-Instruct-2507 llama.cppQ2_K	137.4	102.7	1.34×	2,386	1,893	1.26×	1 / 1
Qwen3-30B-A3B-Instruct-2507 llama.cppQ3_K_M	128.8	97.3	1.32×	2,596	1,708	1.52×	1 / 1
Qwen3-4B-Instruct-2507 llama.cppQ8_0	110.8	60.8	1.82×	5,581	2,686	2.08×	1 / 1
Qwen3.6-27B llama.cppQ3_K_M	29.7	16.7	1.78×	807	373	2.16×	1 / 1
Qwen3.6-35B-A3B llama.cppQ3_K_M	100.3	67.5	1.49×	2,501	1,737	1.44×	1 / 1
Qwen3-8B llama.cppBF16	43.5	18.9	2.30×	3,133	1,376	2.28×	1 / 1
Qwen3-8B llama.cppQ4_1	107.3	51.9	2.07×	2,894	1,535	1.89×	1 / 1

Side A · AMD Radeon RX 7900 XT

Top 25 of 41 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	368.6 TG128	23,972 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	367.7 TG128	23,718 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B llama.cpp b10809 (5266f24da)Q8_0	AMD Radeon RX 7900 XT ROCm	313.7 TG128	24,691 PP512	arki05	11 Sep 2026	View Benchmark
Llama-3.2-3B-Instruct llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	172.0 TG128	6,980 PP512	arki05	11 Sep 2026	View Benchmark
Llama-3.2-3B-Instruct llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	171.9 TG128	6,832 PP512	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	160.1 TG128	3,502 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	147.8 TG128	5,364 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	147.1 TG128	5,337 PP512	arki05	11 Sep 2026	View Benchmark
Llama 3.2 3B Instruct llama.cpp b10809 (5266f24da)Q8_0	AMD Radeon RX 7900 XT ROCm	142.3 TG128	7,210 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q2_K	AMD Radeon RX 7900 XT ROCm	137.4 TG128	2,386 PP512	arki05	11 Sep 2026	View Benchmark
Gpt-Oss-20B llama.cpp b10809 (5266f24da)F16	AMD Radeon RX 7900 XT ROCm	128.8 TG128	3,604 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q3_K_M	AMD Radeon RX 7900 XT ROCm	128.8 TG128	2,596 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	128.6 TG128	2,661 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	128.5 TG128	2,820 PP512	arki05	11 Sep 2026	View Benchmark
Llama-3.1-8B-Instruct llama.cpp b10809 (5266f24da)Q4_0	AMD Radeon RX 7900 XT ROCm	117.4 TG128	3,233 PP512	arki05	11 Sep 2026	View Benchmark
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
Gemma-4-E4B-It llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	111.0 TG128	4,443 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 llama.cpp b10809 (5266f24da)Q8_0	AMD Radeon RX 7900 XT ROCm	110.8 TG128	5,581 PP512	arki05	11 Sep 2026	View Benchmark
Gemma-4-E4B-It llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	109.3 TG128	4,369 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
Qwen3.6-35B-A3B llama.cpp b10809 (5266f24da)Q3_K_M	AMD Radeon RX 7900 XT ROCm	100.3 TG128	2,501 PP512	arki05	11 Sep 2026	View Benchmark
Llama-3.1-8B-Instruct llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	97.5 TG128	3,150 PP512	arki05	11 Sep 2026	View Benchmark
Llama-3.1-8B-Instruct llama.cpp b10809 (5266f24da)Q4_K_M	AMD Radeon RX 7900 XT ROCm	97.1 TG128	3,172 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

Side B · Apple M5 Pro

Top 25 of 129 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
ivnle/tinystories-lay8-hs512-hd8-33M BaseRT 0.2.4Q4	Apple M5 Pro Metal	2,068.0 TG128	190,107 PP512	arki05	17 Sep 2026	View Benchmark
Tinystories Lay8 Hs512 Hd8 33M llama.cpp b10809 (5266f24da)Q4_0	Apple M5 Pro BLAS + Metal	1,443.3 TG128	124,181 PP512	arki05	17 Sep 2026	View Benchmark
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
basecompute/gemma-3-1b-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	293.1 TG128	15,066 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
basecompute/gemma-3-1b-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	270.4 TG128	13,717 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q4	Apple M5 Pro Metal	235.4 TG128	8,040 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	229.1 TG128	11,673 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B-Base BaseRT 0.2.4Q4	Apple M5 Pro Metal	218.2 TG128	2,645 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B BaseRT 0.2.4Q4	Apple M5 Pro Metal	217.7 TG128	2,641 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q4	Apple M5 Pro Metal	210.3 TG128	7,268 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-3-1b-it BaseRT 0.2.4Q8	Apple M5 Pro Metal	210.3 TG128	15,061 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	206.3 TG128	10,528 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Llama-3.2-1B-Instruct BaseRT 0.2.4Q4	Apple M5 Pro Metal	205.3 TG128	12,067 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/gemma-4-E2B-it BaseRT 0.2.4Q4	Apple M5 Pro Metal	144.6 TG128	13,240 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-1.7B BaseRT 0.2.4Q8	Apple M5 Pro Metal	139.7 TG128	8,043 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B-Base BaseRT 0.2.4Q8	Apple M5 Pro Metal	131.4 TG128	2,642 PP512	arki05	11 Sep 2026	View Benchmark