Qwen3
Qwen · 11 models
- Sizes
- 752M–235B
- Downloads, last 30 days
- 50.2M
- Top Arena score
- 1419
- Built on them
- 27,424
Models
| Model | Params | Score |
|---|---|---|
| 752M | — | |
| 2.0B | — | |
| 4.0B | — | |
| 4.0B | — | |
| 8.2B | — | |
| 14.8B | — | |
| 30.5B | 1317 | |
| 30.5B | 1384 | |
| 32.8B | 1340 | |
| 235B | 1394 | |
| 235B | 1419 |
Built on these models
- Quantizations
- 3,231
- Fine-tunes
- 10,585
- Adapters
- 13,430
- Merges
- 178
Discussed, past year
- За считанные минуты локальная ИИ модель моделирует корпус для ESP32C3 #ai #qwen3

Qwen3-0.6B· Oct 2712.3K likes
- Qwen3-TTS family is now open sourced: Voice design, clone, and generation

Qwen3-0.6B· Jan 22744 points
- How to Clone Voice Locally in Any Language for Free with Qwen3 TTS

Qwen3-0.6B· Aug 23167 likes
- Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution

Qwen3-0.6B· May 15246 points
- Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions

Qwen3-0.6B· Jun 21215 points
- Show HN: Qwen3-4B with the AI writing tics trained out

Qwen3-0.6B· Oct 19158 points