GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
jxx123
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
jxx123
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
| meals | model | TIR (70–180) | TBR (<70) | survived |
|---|---|---|---|---|
| announced | v15 (Qwen3-4B) | 68.8 | 13.2 | 7/9 |
| announced | this (Qwen3.5-4B) | 80.8 | 2.1 | 9/9 |
| unannounced | v15 | 68.9 | 10.3 | 8/9 |
| unannounced | this | 73.8 | 2.2 | 9/9 |
| unannounced | Gemini teacher | 73.9 | 3.0 | 9/9 |
adapter_model.safetensors — LoRA adapter (rank 32, all-linear targets; the
hybrid linear-attention layers need all-linear). Merge onto Qwen/Qwen3.5-4B.*-f16.gguf — merged f16 GGUF, already patched for llama.cpp/Ollama
(Qwen3.5's phantom MTP block removed: block_count −1, nextn_predict_layers=0).
Quantize + serve: ollama create loop-qwen35 --quantize q4_K_M -f Modelfile
(needs Ollama ≥ 0.32). Modelfile: FROM *-f16.gguf / TEMPLATE {{ .Prompt }} /
PARAMETER num_ctx 4096 / PARAMETER temperature 0.transformers 5.x + torch 2.6 (matched torchvision/torchaudio), LoRA r32
target_modules=all-linear, 2 epochs, eff. batch 32, lr 2e-4, max-seq 4096.
Data: jxx123/loop-qwen-v8-sft (distill_sft_v16.jsonl). Reason-before-act
(concise clinical rationale) output format. Trained on 21 non-held-out patients only.
⚠️ Research / simulation only — not a medical device.