Models · Qwen (Alibaba) · Out sinceReleased 27 Apr 2026
Qwen3.6 35B A3B
Qwen3.6 35B A3B is made by Qwen (Alibaba). We don't have enough test results yet to rank it. It's cheap to use. Its makers have published it, so you can run it on your own servers.
Auto-created from OpenRouter catalog; verify details.
- —
- —
- —
- Cheap$0.15 / $1
- $0.36
- 262K
- —
- 9 (9 independent9 indep.)
- 27 Apr 2026
- Qwen (Alibaba)
- —
Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.
You can't choose how long this one thinks.
No adjustable reasoning setting listed.
OpenRouter is a service that gives access to many AI models in one place. This model is listed there as qwen/qwen3.6-35b-a3b.
Route it as qwen/qwen3.6-35b-a3b at $0.15 in / $1 out per 1M tokens, 262K context. Listed since 27 Apr 2026.
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Run it yourself
Self-hosting
On your own servers,Licence, sizeunder your own control.and hardware.
- Yes
- 35B / 3B
- No
Runs on a powerful laptop or workstation.
≤ 24 GB at 4-bit (one consumer GPU / 32 GB Mac). Weights ≈ 37 GB at 8-bit, 19 GB at 4-bit (+10–30% for KV cache). MoE: 3B active per token.
Languages: Languages: Not listed in 3.6 card; Qwen3.5 card: 201 languages and dialects.
Training it further: Fine-tuning: No recipe in card. Same-architecture base Qwen/Qwen3.5-35B-A3B-Base (Apache 2.0) is the best Qwen MoE starting point for continued pretraining/SFT.
Quantisations: bf16, fp8 (Qwen/Qwen3.6-35B-A3B-FP8). Engines: SGLang, vLLM, KTransformers, Transformers.
Download (Hugging Face)Weights on Hugging Face ↗huggingface.co ↗huggingface.co ↗
Every test result
Every result
All the numbers,with where they came from.
Every result we've found for this model, with who measured it and a link to where we read it.
All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.
| NotesNotes | ||||||
|---|---|---|---|---|---|---|
| AA-LCR | 71.7% | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b |
| AA-Omniscience Index | -22.2 | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b; AA-Omniscience Index (-100..100) |
| Artificial Analysis Intelligence Index | 18.2 | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b |
| Artificial Analysis output speed | 125 tok/s | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b; median output tokens/sec across AA-tracked API providers (not a self-hosted measurement) |
| GPQA Diamond | 84.1% | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b |
| Humanity's Last Exam | 22.2% | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b |
| SciCode | 36.6% | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b |
| SWE-rebench | 24.7% | DefaultQwen3.6-35B-A3B | Independent testIndependentSWE-rebench (Nebius) ↗ | 1 Oct 2026 | SWE-rebench standard scaffold | time window 2026-05-15..2026-07-01 (111 problems, 65 repos); ±0.79; pass@5 43.2%; $0.27/problem |
| Terminal-Bench 2.1 | 44.9% | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | 1 Oct 2026 | — | AA slug qwen3-6-35b-a3b |