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: 12
Like-for-like pairs: 3
Chips available: 7

Compare

Side A

Side B

Model

Runtime

Runtime version

Quantisation

Backend

Prefill size

Decode size

Cooldown

8 runs vs 4 runs · 3 like-for-like pairs

Held fixedModel: Qwen3 30B A3B Instruct 2507Prefill: PP512Decode: TG128

A side mixes quantisations. Pick a quantisation to compare the same weights.
The sides differ in conditioning, 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 3 like-for-like pairs.

Decode: 0.75×-25.2%
Prefill: 0.70×-29.5%

Side A

Apple M5 Pro

8 runs

1 contributor

Latest 11 Sep 2026

Decode · TG128: 95.1tok/s median
best 104.0 · worst 78.9
Prefill · PP512: 1,838tok/s median
best 3,680 · worst 1,644

Models: Qwen3-30B-A3B-Instruct-2507
Runtimes: BaseRTllama.cpp
Versions: BaseRT 0.2.4, llama.cpp b10809 (5266f24da)
Quantisations: Q2_K, Q3_K_M, Q4, Q4_K_M, Q5_K_M, Q6_K
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

AMD Radeon RX 7900 XT

4 runs

1 contributor

Latest 11 Sep 2026

Decode · TG128: 128.7tok/s median
best 137.4 · worst 128.5
Prefill · PP512: 2,629tok/s median
best 2,820 · worst 2,386

Models: Qwen3-30B-A3B-Instruct-2507
Runtimes: llama.cpp
Versions: llama.cpp b10809 (5266f24da)
Quantisations: Q2_K, Q3_K_M, Q4_K_M
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
Runtime	BaseRT, llama.cpp	llama.cpp
Runtime version	BaseRT 0.2.4, llama.cpp b10809 (5266f24da)	llama.cpp b10809 (5266f24da)
Quantisation	Q2_K, Q3_K_M, Q4, Q4_K_M, Q5_K_M, Q6_K	Q2_K, Q3_K_M, Q4_K_M
Backend	BLAS + Metal, Metal	ROCm
Conditioning	runtime_native_warmup, warmup_only	runtime_native_warmup
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
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M	95.1	128.5	0.74×	1,838	2,741	0.67×	2 / 2
Qwen3-30B-A3B-Instruct-2507 llama.cppQ2_K	102.7	137.4	0.75×	1,893	2,386	0.79×	1 / 1
Qwen3-30B-A3B-Instruct-2507 llama.cppQ3_K_M	97.3	128.8	0.76×	1,708	2,596	0.66×	1 / 1

Side A · Apple M5 Pro

Top 8 of 8 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
basecompute/Qwen3-30B-A3B-Instruct-2507 BaseRT 0.2.4Q4	Apple M5 Pro Metal	104.0 TG128	3,680 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q2_K	Apple M5 Pro BLAS + Metal	102.7 TG128	1,893 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q3_K_M	Apple M5 Pro BLAS + Metal	97.3 TG128	1,708 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	95.2 TG128	1,845 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q4_K_M	Apple M5 Pro BLAS + Metal	95.0 TG128	1,831 PP512	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-30B-A3B-Instruct-2507 BaseRT 0.2.4Q4	Apple M5 Pro Metal	92.2 TG128	3,305 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q5_K_M	Apple M5 Pro BLAS + Metal	84.7 TG128	1,644 PP512	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cpp b10809 (5266f24da)Q6_K	Apple M5 Pro BLAS + Metal	78.9 TG128	1,646 PP512	arki05	11 Sep 2026	View Benchmark

Side B · AMD Radeon RX 7900 XT

Top 4 of 4 runs by decode throughput.

Model / format	Chip / backend	Decode	Prefill	Contributor	Date	Report
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
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