Models

Loading community benchmarks…

← All models

Community benchmarks

Qwen3.6 27B

Submitted benchmarks for Qwen3.6 27B. 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: 33
Chips tested: 10
Contributors: 2

Model identity

Grouped as Qwen/Qwen3.6-27B. 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/Qwen3.6-27B, Qwen3.6-27B, Qwen3.6-27B-cuda-q4mix, Qwen3.6-27B-cuda-q8, Qwen3.6-27B-Q4, Qwen3.6-27B-Q8, Qwen/Qwen3.6-27B. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/Qwen3.6-27B/Qwen3.6-27B-Q4.base (opens in a new tab)BaseRTQ4· 9 runs
basecompute/Qwen3.6-27B/Qwen3.6-27B-Q8.base (opens in a new tab)BaseRTQ8· 5 runs
unsloth/Qwen3.6-27B-GGUF/Qwen3.6-27B-Q4_K_M.gguf (opens in a new tab)llama.cppQ4_K_M· 3 runs
unsloth/Qwen3.6-27B-GGUF/Qwen3.6-27B-UD-Q3_K_XL.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 Qwen3.6 27B. 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

Qwen3.6-27B-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	38.4 tok/s TG128 @ 1 ctx	409 tok/s PP512	22,671.2 MiB	basecompute	19 Oct 2026	View Benchmark
Qwen3.6-27B-cuda-q8 BaseRTQ8 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.	unknown CUDA	7.5 tok/s TG128 @ 1 ctx	1,700 tok/s PP512	28,184.2 MiB	basecompute	14 Oct 2026	View Benchmark
Qwen3.6-27B-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.	unknown CUDA	12.3 tok/s TG128 @ 1 ctx	1,729 tok/s PP512	18,320.0 MiB	basecompute	14 Oct 2026	View Benchmark
Qwen3.6-27B-Q8 BaseRTQ8 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	11.0 tok/s TG128 @ 1 ctx	142 tok/s PP512	37,653.0 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.6-27B-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	18.0 tok/s TG128 @ 1 ctx	143 tok/s PP512	22,685.0 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.6-27B-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.	unknown CUDA	7.5 tok/s TG128 @ 1 ctx	1,700 tok/s PP512	28,070.2 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.6-27B-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.	unknown CUDA	11.5 tok/s TG128 @ 1 ctx	1,711 tok/s PP512	18,318.9 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.6-27B-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.	unknown CUDA	14.1 tok/s TG128 @ 1 ctx	385 tok/s PP512	16,138.1 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.6-27B-Q8 BaseRTQ8 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	17.5 tok/s TG128 @ 1 ctx	222 tok/s PP512	37,637.6 MiB	basecompute	4 Oct 2026	View Benchmark
Qwen3.6-27B-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	36.8 tok/s TG128 @ 1 ctx	281 tok/s PP512	22,664.1 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-27B-Q8 BaseRTQ8 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	22.1 tok/s TG128 @ 1 ctx	280 tok/s PP512	37,631.9 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-27B-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	30.3 tok/s TG128 @ 1 ctx	221 tok/s PP512	22,666.8 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-27B-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	17.9 tok/s TG128 @ 1 ctx	80 tok/s PP512	22,669.0 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-27B-Q8 BaseRTQ8 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	11.0 tok/s TG128 @ 1 ctx	83 tok/s PP512	37,635.9 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-27B-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	8.4 tok/s TG128 @ 1 ctx	1,146 tok/s PP512	27,413.3 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-27B-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	7.5 tok/s TG128 @ 1 ctx	1,141 tok/s PP512	27,414.9 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-27B-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	12.3 tok/s TG128 @ 1 ctx	1,127 tok/s PP512	18,021.2 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-27B-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	13.0 tok/s TG128 @ 1 ctx	344 tok/s PP512	15,228.4 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-27B llama.cppQ4_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.	Tesla T10/Tesla T10/Tesla T10/Tesla T10 CUDA	48.0 tok/s TG128	1,174 tok/s PP512	10.8 MiB	arki05	17 Sep 2026	View Benchmark
Qwen3.6-27B 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	32.5 tok/s TG128	783 tok/s PP512	16,952.8 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-27B 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	33.7 tok/s TG128	782 tok/s PP512	16,194.4 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-27B 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	36.8 tok/s TG128	739 tok/s PP512	13,959.1 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-27B 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	29.3 tok/s TG128	840 tok/s PP512	18,659.5 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-27B 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	29.8 tok/s TG128	841 tok/s PP512	17,901.1 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-27B 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	29.7 tok/s TG128	807 tok/s PP512	15,665.9 MiB	arki05	11 Sep 2026	View Benchmark