Models

Loading community benchmarks…

← All models

Community benchmarks

Qwen3.6 35B A3B

Submitted benchmarks for Qwen3.6 35B A3B. 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: 18
Chips tested: 8
Contributors: 3

Model identity

Grouped as Qwen/Qwen3.6-35B-A3B. 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/Qwen3.6-35B-A3B, Qwen3.6-35B-A3B, Qwen3.6-35B-A3B-cuda-q4mix, Qwen3.6-35B-A3B-cuda-q8, Qwen3.6-35B-A3B-Q4, Qwen3.6-35B-A3B-Q8. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/Qwen3.6-35B-A3B/Qwen3.6-35B-A3B-Q4.base (opens in a new tab)BaseRTQ4· 5 runs
basecompute/Qwen3.6-35B-A3B/Qwen3.6-35B-A3B-Q8.base (opens in a new tab)BaseRTQ8· 5 runs
unsloth/Qwen3.6-35B-A3B-GGUF/Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf (opens in a new tab)llama.cppQ3_K_M· 3 runs
unsloth/Qwen3.6-35B-A3B-GGUF/Qwen3.6-35B-A3B-UD-Q4_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 35B A3B. 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/Qwen3.6-35B-A3B 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	119.6 tok/s TG128	1,540 tok/s PP512	3,727.4 MiB	lukas	10 Sep 2026	View Benchmark
basecompute/Qwen3.6-35B-A3B 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	113.2 tok/s TG128	1,275 tok/s PP512	2,765.7 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-35B-A3B 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	67.5 tok/s TG128	1,737 tok/s PP512	16,676.6 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-35B-A3B 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	61.5 tok/s TG128	1,673 tok/s PP512	21,935.8 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-35B-A3B 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	61.5 tok/s TG128	1,533 tok/s PP512	25,973.1 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-35B-A3B 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	100.3 tok/s TG128	2,501 tok/s PP512	17,927.9 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-35B-A3B 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	124.1 tok/s TG128	2,597 tok/s PP512	16,221.2 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	84.3 tok/s TG128 @ 1 ctx	2,028 tok/s PP512	16,676.7 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	72.2 tok/s TG128 @ 1 ctx	232 tok/s PP512	59,584.5 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	72.8 tok/s TG128 @ 1 ctx	2,279 tok/s PP512	14,955.8 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	70.8 tok/s TG128 @ 1 ctx	247 tok/s PP512	59,566.5 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	54.4 tok/s TG128 @ 1 ctx	2,188 tok/s PP512	28,757.9 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	55.4 tok/s TG128 @ 1 ctx	2,181 tok/s PP512	28,760.0 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	94.2 tok/s TG128 @ 1 ctx	278 tok/s PP512	2,749.9 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	109.5 tok/s TG128 @ 1 ctx	913 tok/s PP512	3,677.9 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	110.8 tok/s TG128 @ 1 ctx	910 tok/s PP512	3,678.1 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	133.0 tok/s TG128 @ 1 ctx	922 tok/s PP512	2,747.0 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.6-35B-A3B-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	139.7 tok/s TG128 @ 1 ctx	886 tok/s PP512	2,747.8 MiB	basecompute	20 Sep 2026	View Benchmark