Qwen/Qwen3.6-27B-FP8
Parameters27.8B
Context256K
Input → outputimage + text → text
Licenseapache-2.0
PrecisionF8_E4M3 · fp8
ArchitectureQwen3_5ForConditionalGeneration
ReleasedApr 21, 2026
Downloads1.7M
Based on Qwen/Qwen3.6-27B
Other sizes and formats in the family
| Model | Params | Precision | Downloads |
|---|---|---|---|
| Qwen/Qwen3.6-35B-A3B-FP8fp8 | 36B | F8_E4M3 | 4.2M |
| Qwen/Qwen3.6-35B-A3B | 36B | BF16 | 3.6M |
| Qwen/Qwen3.6-27B | 27.8B | BF16 | 2.3M |
This release in the news
No coverage of this exact release yet.
Recent news about Qwen
- Oct 11, 2026 · Opinion / analysis[P] Pecision models that score every allowed label from the logits: Jebadiah v2.1 (27B, 9B), open weights and self-run benchmark results [P]
- Oct 11, 2026 · Opinion / analysisPSA: DeepSeek V4.1 Flash habitually exfiltrates API keys. It is dangerously misaligned and may be hazardous to use
- Oct 11, 2026 · Opinion / analysisQwen 3.8 27B Q5 vs Qwen 3.8 Next Q3_S for document analysis
- Oct 11, 2026 · Open-source releaseConverting dense models into Mixture-of-Experts
- Oct 11, 2026 · Tutorial / explainerRunning Next Flash IQ3_XXS at ~70 tok/s with 100k context or 2 instances of Qwen 3.6 35B A3B IQ4 at ~145 tok/s with 256k all on $500 of ex mining BC-250 boards
- Oct 11, 2026 · Opinion / analysisQwen3.8 Flash Next fixed my GNOME extension
- Oct 11, 2026 · Tutorial / explainerBuilding a 4x R9700 setup for a 10 person startup
- Oct 11, 2026 · Tutorial / explainerOMG! If you have a Mac with 64GB, try Qwen3.8-Flash-Next-oQ4e-mtp with oMLX!