Models

Loading community benchmarks…

← All models

Community benchmarks

Qwen3.5 2B

Submitted benchmarks for Qwen3.5 2B. 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: 25
Chips tested: 8
Contributors: 3

Model identity

Grouped as Qwen/Qwen3.5-2B. 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/Qwen3.5-2B, Qwen3.5-2B-cuda-q4mix, Qwen3.5-2B-cuda-q8, Qwen3.5-2B-Q4, Qwen3.5-2B-Q8. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/Qwen3.5-2B/Qwen3.5-2B-Q4.base (opens in a new tab)BaseRTQ4· 11 runs
basecompute/Qwen3.5-2B/Qwen3.5-2B-Q8.base (opens in a new tab)BaseRTQ8· 8 runs

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 Qwen3.5 2B. 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/Qwen3.5-2B 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	217.7 tok/s TG128	2,641 tok/s PP512	2,071.0 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B 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	130.7 tok/s TG128	2,638 tok/s PP512	2,955.2 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3.5-2B 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 Metal	58.6 tok/s TG128	1,203 tok/s PP512	1,732.6 MiB	skogul97	11 Sep 2026	View Benchmark
Qwen3.5-2B-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	181.6 tok/s TG128 @ 1 ctx	4,185 tok/s PP512	1,768.9 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-2B-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	151.5 tok/s TG128 @ 1 ctx	6,837 tok/s PP512	1,984.5 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-2B-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	113.5 tok/s TG128 @ 1 ctx	6,754 tok/s PP512	2,592.4 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-2B-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	301.7 tok/s TG128 @ 1 ctx	1,718 tok/s PP512	2,065.5 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-2B-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	205.4 tok/s TG128 @ 1 ctx	1,721 tok/s PP512	2,950.5 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3.5-2B-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	141.5 tok/s TG128 @ 1 ctx	400 tok/s PP512	2,953.7 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-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	192.9 tok/s TG128 @ 1 ctx	429 tok/s PP512	2,068.8 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-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	222.9 tok/s TG128 @ 1 ctx	1,756 tok/s PP512	2,949.7 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-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	306.7 tok/s TG128 @ 1 ctx	1,759 tok/s PP512	2,066.4 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-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 Pro Metal	113.5 tok/s TG128 @ 1 ctx	1,138 tok/s PP512	2,954.1 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-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 Pro Metal	179.1 tok/s TG128 @ 1 ctx	1,150 tok/s PP512	2,070.3 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3.5-2B-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	179.0 tok/s TG128 @ 1 ctx	6,868 tok/s PP512	1,971.0 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-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	149.2 tok/s TG128 @ 1 ctx	18,209 tok/s PP512	2,264.6 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-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	109.1 tok/s TG128 @ 1 ctx	17,984 tok/s PP512	2,941.0 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-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	184.7 tok/s TG128 @ 1 ctx	2,096 tok/s PP512	2,083.4 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-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 Pro Metal	172.0 tok/s TG128 @ 1 ctx	1,833 tok/s PP512	2,083.1 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-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	139.1 tok/s TG128 @ 1 ctx	2,070 tok/s PP512	2,970.5 MiB	basecompute	9 Oct 2026	View Benchmark
Qwen3.5-2B-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 Pro Metal	112.3 tok/s TG128 @ 1 ctx	1,812 tok/s PP512	2,968.3 MiB	basecompute	11 Oct 2026	View Benchmark
Qwen3.5-2B-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	148.7 tok/s TG128 @ 1 ctx	18,297 tok/s PP512	2,658.6 MiB	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-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	110.5 tok/s TG128 @ 1 ctx	17,866 tok/s PP512	3,441.5 MiB	basecompute	14 Oct 2026	View Benchmark
Qwen3.5-2B-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	232.5 tok/s TG128 @ 1 ctx	5,415 tok/s PP512	2,954.0 MiB	basecompute	19 Oct 2026	View Benchmark
Qwen3.5-2B-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	311.3 tok/s TG128 @ 1 ctx	5,484 tok/s PP512	2,069.0 MiB	basecompute	19 Oct 2026	View Benchmark