Qwen3.8 27B
Open-weight dense 27B; the strongest small local-sized model on LLM Chess. A candidate to pull for local games.
- Vendor
- Alibaba
- Kind
- llm
- Tier
- small
- Weights
- open
- Released
- 2026-08
- Context
- 1,024k tokens
Our Go rating
Not rated yet: ratings come from tournament games against bots of known strength. See the leaderboard.
Games here
No published game yet.
Benchmarks
| Measure | Value | Unit | As of | Source |
|---|---|---|---|---|
| LMArena text | 1,433 | Elo | 2026-11 | LMArena (arena.ai) Text leaderboard, page dated 2026-11-09 |
| Artificial Analysis Intelligence Index (xhigh) | 20 | index points | 2026-11 | Artificial Analysis Intelligence Index (current version, composite of |
Other games
| Measure | Value | Unit | As of | Source |
|---|---|---|---|---|
| LLM Chess (q4_k_m local quant), ±166 | 846 | Elo (chess.com-anchored) | 2026-11-05 | LLM Chess (Saplin) Elo vs random player and Komodo Dragon, chess.com-a |
How we run it
- needs-key
openrouter·qwen/qwen3.8-27b— OPENROUTER_API_KEY not set - untested
ollama·qwen3.8:27b— not pulled on this Mac; tag not verified