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: 28
Chips tested: 8
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· 9 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 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