GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
chorcat
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
chorcat
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
| Base model | Qwen/Qwen3-0.6B (600,637,440 parameters) |
| Precision | 4-bit NF4 (QLoRA) |
Rank r | 16, alpha 32 |
| Adapted matrices | k_proj, o_proj, q_proj, v_proj |
| Trainable parameters | 4,587,520 (0.764 %) |
| Training samples | 100,000 games |
| Steps | 1,500 |
| Weights on the device | 851 MB |
| Peak memory while training | 2361 MB |
The games are the same ones the project's own decoder trains on, from the same month, held out against the same validation split. Each is rendered as the movetext a human would paste into a chess site, with the two ratings as PGN tags:
text
[WhiteElo "2015"] [BlackElo "2028"]1. e4 c6 2. d4 d5 3. exd5 cxd5 4. Bd3 Nf6 ... 1-0Measured with the project's own harness -- the same validation positions, the same puzzle split and the same Stockfish ladder as every other stage -- so the two sides differ in their representation and in nothing else.
| Metric | Value |
|---|---|
| Legal moves written, no mask | 62.50 % |
| Top-1 next move | 12.5 % |
| Puzzles solved | 0.9 % |
| Estimated Elo | < 807 (one-sided 95 % bound; every game lost) |
A model whose vocabulary is the set of legal moves can only be wrong one way: a legal move in the wrong position. A model writing SAN has three more.
| Outcome | Share |
|---|---|
| legal | 62.50 % |
| illegal here | 33.70 % |
| not a move at all | 2.90 % |
| ambiguous SAN | 0.90 % |
| nothing written | 0.00 % |
qwen3-pgn-qlora: every stage of the course, the same suite, the same day.uv run rukh pull qwen3-pgn-qlora.apache-2.0.