Models

Loading community benchmarks…

← All models

Community benchmarks

Qwen3.8 27B

Submitted benchmarks for Qwen3.8 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: 20
Chips tested: 8
Contributors: 5

Model identity

Grouped as Qwen/Qwen3.8-27B. 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.. 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/Qwen3.8-27B, Qwen3.8-27B, Qwen3.8-27B-Q4, Qwen3.8-27B-Q8. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/Qwen3.8-27B/Qwen3.8-27B-Q4.base (opens in a new tab)BaseRTQ4· 10 runs
basecompute/Qwen3.8-27B/Qwen3.8-27B-Q8.base (opens in a new tab)BaseRTQ4· 6 runs
unsloth/Qwen3.8-27B-GGUF/Qwen3.8-27B-UD-Q4_K_M.gguf (opens in a new tab)llama.cppQ4_K_M· 2 runs
unsloth/Qwen3.8-27B-GGUF/Qwen3.8-27B-Q4_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 Qwen3.8 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

basecompute/Qwen3.8-27B 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	34.0 tok/s TG128	589 tok/s PP512	14,842.1 MiB	basecompute	10 Sep 2026	View Benchmark
Qwen3.8-27B-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	31.6 tok/s TG128	222 tok/s PP512	22,738.8 MiB	fabian	10 Sep 2026	View Benchmark
basecompute/Qwen3.8-27B 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	19.7 tok/s TG128	589 tok/s PP512	22,598.1 MiB	lukas	10 Sep 2026	View Benchmark
Qwen3.8-27B llama.cppQ4_1 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 H100 80GB HBM3 × 8 CUDA	95.3 tok/s TG128	2,513 tok/s PP512	17,724.0 MiB	sarthak247	11 Sep 2026	View Benchmark
basecompute/Qwen3.8-27B 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	16.5 tok/s TG128	327 tok/s PP512	19,848.7 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.8-27B BaseRTQ4· 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	10.6 tok/s TG128	355 tok/s PP512	21,918.2 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.8-27B 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.	Apple M4 Max BLAS + Metal	22.9 tok/s TG128	243 tok/s PP512	16,800.7 MiB	fabian	11 Sep 2026	View Benchmark
basecompute/Qwen3.8-27B 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	21.5 tok/s TG128	590 tok/s PP512	22,598.4 MiB	lukas	15 Sep 2026	View Benchmark
basecompute/Qwen3.8-27B 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	20.7 tok/s TG128	599 tok/s PP512	22,597.8 MiB	lukas	15 Sep 2026	View Benchmark
basecompute/Qwen3.8-27B 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	21.5 tok/s TG128	594 tok/s PP512	22,598.0 MiB	lukas	15 Sep 2026	View Benchmark
Qwen3.8-27B 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	48.1 tok/s TG128	910 tok/s PP512	11.0 MiB	arki05	17 Sep 2026	View Benchmark
Qwen3.8-27B 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.	Tesla T10/Tesla T10/Tesla T10/Tesla T10 CUDA	46.0 tok/s TG128	1,132 tok/s PP512	11.1 MiB	arki05	17 Sep 2026	View Benchmark
Qwen3.8-27B-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	18.2 tok/s TG128 @ 1 ctx	82 tok/s PP512	22,669.1 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-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	13.1 tok/s TG128 @ 1 ctx	1,131 tok/s PP512	17,146.0 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 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	7.6 tok/s TG128 @ 1 ctx	1,152 tok/s PP512	27,413.4 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 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	7.5 tok/s TG128 @ 1 ctx	1,127 tok/s PP512	27,414.0 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 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	11.0 tok/s TG128 @ 1 ctx	82 tok/s PP512	37,636.3 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 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	11.0 tok/s TG128 @ 1 ctx	82 tok/s PP512	37,636.5 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.8-27B-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	38.0 tok/s TG128 @ 1 ctx	282 tok/s PP512	22,666.1 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.8-27B-Q8 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	22.1 tok/s TG128 @ 1 ctx	280 tok/s PP512	37,635.2 MiB	basecompute	20 Sep 2026	View Benchmark