GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
lewismoten
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
lewismoten
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Submit only a raw move history made from a through i—one letter for each occupied square, in chronological order. The deployment template is literal <bos>{{ .Prompt }}. Use temperature 0, a 16-token context, and generate exactly one token.
!.Example raw history: a
Checked F16 fixture result: e
Qwen2MoeForCausalLM, trained from scratch| Artifact | Runtime evidence |
|---|---|
| F16 GGUF | 978,003 raw-history cases; 0 failures; local Ollama fixture verified |
| Q6_K GGUF | 978,003 raw-history cases; 0 failures |
| Q4_K_M GGUF | 978,003 raw-history cases; 0 failures |
| Source checkpoint | Hugging Face-compatible config, tokenizer, and safetensors weights |
The Q4_K_M release is truthfully mixed storage: narrow tensors that cannot use a particular block layout remain F16/F32 or Q6_K where required. No Q8_0 artifact is provided because the model's 36- and 18-wide tensors do not meet Q8_0 block-size requirements.
Use the F16 GGUF with a raw-completion template:
text
FROM ./palace9-qwen2moe-raw-history-f16.ggufPARAMETER num_ctx 16PARAMETER num_predict 1PARAMETER temperature 0TEMPLATE """<bos>{{ .Prompt }}"""Then import with ollama create palace-9:f16 -f Modelfile.
The Ollama package contains only the GGUF and Modelfile configuration. The playable board, weight inspector, and fictional visual overlay run independently in browser JavaScript and are available through the source repository and live demo.
This is a small, fictional 3×3 tic-tac-toe state policy. It has no external command authority, no real-world data, and no operational-system capability. The browser demo's map, DEFCON display, trajectories, and cipher graphics are fictional presentation layers.
The release includes source checkpoint files, GGUF artifacts, checksums, a model card, and machine-readable validation evidence. The exhaustive runtime gates cover 294,777 legal histories and 683,226 invalid histories (978,003 total) per F16, Q6_K, and Q4_K_M artifact, with zero failures.
PALACE-9 was designed and directed by Lewis Moten. Its code and documentation were developed with assistance from GPT-5.6-terra Med, accessed through Hermes and using Honcho for context and project-memory support. Lewis Moten remains the project designer, maintainer, and publisher.
Copyright 2026 Lewis Moten. Released under Apache-2.0.
FROM ./palace9-qwen2moe-raw-history-f16.ggufPARAMETER num_ctx 16PARAMETER num_predict 1PARAMETER temperature 0TEMPLATE """<bos>{{ .Prompt }}"""