Models

Loading community benchmarks…

← All models

Community benchmarks

Qwen3 30B A3B Instruct 2507

Submitted benchmarks for Qwen3 30B A3B Instruct 2507. Browse individual runs and their measurement settings, or open the report JSON for full benchmark details.

Compare chips Compare runtimes Add your benchmark

Submitted runs: 23
Chips tested: 7
Contributors: 2

Model identity

Grouped as Qwen/Qwen3-30B-A3B-Instruct-2507. The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. · Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled.. Artifact verification confirms published model bytes, not that a community-submitted benchmark was honestly executed. Hover or tap a label for what it means.

This model group collects runs reported as basecompute/Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Instruct-2507-cuda-q4mix, Qwen3-30B-A3B-Instruct-2507-cuda-q8, Qwen3-30B-A3B-Instruct-2507-Q4. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/Qwen3-30B-A3B-Instruct-2507/Qwen3-30B-A3B-Instruct-2507-Q4.base (opens in a new tab)BaseRTQ4· 6 runs
unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF/Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf (opens in a new tab)llama.cppQ4_K_M· 3 runs
unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF/Qwen3-30B-A3B-Instruct-2507-UD-Q2_K_XL.gguf (opens in a new tab)llama.cppQ2_K

Benchmark results

Peak throughput is the highest reported value and may come from different runs. Compare model, quantisation, backend, and token counts before drawing conclusions. Model verification identifies published artifact bytes; community benchmark execution is not remotely attested.

Individual runs for Qwen3 30B A3B Instruct 2507. Throughput is in tokens per second; dates use your browser timezone. Hover a date for the exact local time.
Model / runtime / format	Chip / backend	Decode	Prefill	Peak process memory

Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M4 Max Metal	139.8 tok/s TG128 @ 1 ctx	1,789 tok/s PP512	1,470.0 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M3 Ultra Metal	137.1 tok/s TG128 @ 1 ctx	2,287 tok/s PP512	1,466.5 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M1 Max Metal	87.7 tok/s TG128 @ 1 ctx	901 tok/s PP512	1,471.3 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled.	NVIDIA GB10 CUDA	61.2 tok/s TG128 @ 1 ctx	7,253 tok/s PP512	30,962.8 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-cuda-q8 BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled.	NVIDIA GB10 CUDA	49.4 tok/s TG128 @ 1 ctx	7,315 tok/s PP512	21,317.5 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-cuda-q4mix BaseRTQ4 Nothing in this report ties it to a published model file. Reports from CLI 0.1.0 record only a model name and a file hash, so the run is grouped by the name it reported until it is reconciled.	NVIDIA GB10 CUDA	99.0 tok/s TG128 @ 1 ctx	7,439 tok/s PP512	17,897.6 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	NVIDIA GB10 CUDA	80.7 tok/s TG128 @ 1 ctx	4,715 tok/s PP512	13,752.2 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan	181.3 tok/s TG128	2,827 tok/s PP512	17,816.1 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan	186.7 tok/s TG128	2,868 tok/s PP512	16,990.0 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ3_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan	184.5 tok/s TG128	2,474 tok/s PP512	13,311.2 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ2_K The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan	198.1 tok/s TG128	2,837 tok/s PP512	11,357.9 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT ROCm	128.6 tok/s TG128	2,661 tok/s PP512	19,571.4 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT ROCm	128.5 tok/s TG128	2,820 tok/s PP512	18,741.8 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ3_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT ROCm	128.8 tok/s TG128	2,596 tok/s PP512	15,066.6 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ2_K The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	AMD Radeon RX 7900 XT ROCm	137.4 tok/s TG128	2,386 tok/s PP512	13,115.8 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-30B-A3B-Instruct-2507 BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro Metal	104.0 tok/s TG128	3,680 tok/s PP512	1,481.7 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ6_K The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	78.9 tok/s TG128	1,646 tok/s PP512	25,646.9 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ5_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	84.7 tok/s TG128	1,644 tok/s PP512	22,433.6 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	95.2 tok/s TG128	1,845 tok/s PP512	18,586.3 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	95.0 tok/s TG128	1,831 tok/s PP512	19,412.5 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ3_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	97.3 tok/s TG128	1,708 tok/s PP512	14,908.4 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-30B-A3B-Instruct-2507 llama.cppQ2_K The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro BLAS + Metal	102.7 tok/s TG128	1,893 tok/s PP512	12,958.3 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-30B-A3B-Instruct-2507 BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution.	Apple M5 Pro Metal	92.2 tok/s TG128	3,305 tok/s PP512	1,482.0 MiB	arki05	11 Sep 2026	View Benchmark