GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
modrill
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
modrill
Model Tree
Qwen/Qwen3-4B-Base
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-4B-Base906bfd4b4dc7f14ee4320094d8b41684abff8539q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj), then merged into full-model bf16 safetensors1e-4; context 8192; AdamW; cosine by assistant-token doseqwen3-v4-tail151643max_model_len 8192, vLLM 0.28.0Qwen/Qwen3-4B-Base, same NoThink protocol): 36/256 (14.1%), caps 48chat_template.jinja.<think>; if the template accepts enable_thinking, keep it false.<|endoftext|>) and 151645 (<|im_end|>).model.safetensors (8,822,894,520 bytes): sha256:4309b112b8635695282a1c18f7d9e301862ef028c83e2b000a34caa08b47ef1fOFFICIAL_MERGE_RECEIPT.json is included for merge provenance. LoRA adapter checkpoints are not in this repo.