Models

Loading community benchmarks…

← All models

Community benchmarks

Qwen3 0.6B

Submitted benchmarks for Qwen3 0.6B. 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: 35
Chips tested: 11
Contributors: 5

Model identity

Grouped as Qwen/Qwen3-0.6B. 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. · This report predates artifact identity, so ComputeArena mapped its model name to a model family by hand. The exact model bytes were not verified. · 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/Qwen3-0.6B, Models Qwen Qwen3 0.6B, Qwen3-0.6B, Qwen3-0.6B-cuda-q4, Qwen3-0.6B-cuda-q4mix, Qwen3-0.6B-cuda-q8, Qwen3 0.6B Instruct, Qwen3-0.6B-Q4, Qwen3-0.6B-Q8, Qwen/Qwen3-0.6B. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/Qwen3-0.6B/Qwen3-0.6B-Q4.base (opens in a new tab)BaseRTQ4· 11 runs
basecompute/Qwen3-0.6B/Qwen3-0.6B-Q8.base (opens in a new tab)BaseRTQ8· 8 runs
unsloth/Qwen3-0.6B-GGUF/Qwen3-0.6B-Q4_K_M.gguf (opens in a new tab)llama.cppQ4_K_M· 4 runs
unsloth/Qwen3-0.6B-GGUF/Qwen3-0.6B-Q8_0.gguf

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 0.6B. 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	Contributor

Qwen3-0.6B 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	358.1 tok/s TG128	14,344 tok/s PP512	2,342.6 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B 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	358.3 tok/s TG128	14,509 tok/s PP512	2,333.1 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-0.6B 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	356.2 tok/s TG128	14,552 tok/s PP512	2,333.7 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRTQ8· default-q8 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	311.0 tok/s TG128	18,474 tok/s PP512	1,653.1 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B 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	512.0 tok/s TG128	20,603 tok/s PP512	1,380.7 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRTQ8· default-q8 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	349.8 tok/s TG128	20,366 tok/s PP512	1,653.3 MiB	arki05	11 Sep 2026	View Benchmark
Models Qwen Qwen3 0.6B 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 Max BLAS + Metal	439.1 tok/s TG128	24,365 tok/s PP512	2,396.2 MiB	basecompute	10 Sep 2026	View Benchmark
Qwen3 0.6B Instruct llama.cppQ8_0 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 Max BLAS + Metal	379.0 tok/s TG128	24,983 tok/s PP512	2,544.5 MiB	basecompute	10 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B BaseRTQ8· default-q8 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 Max Metal	549.5 tok/s TG128	33,088 tok/s PP512	1,696.0 MiB	basecompute	10 Sep 2026	View Benchmark
basecompute/Qwen3-0.6B 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 Max Metal	708.3 tok/s TG128	34,136 tok/s PP512	1,554.9 MiB	basecompute	10 Sep 2026	View Benchmark