GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Ttimms
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Ttimms
Model Tree
Kwaipilot/KAT-Coder-V2.5-Dev
Input Modalities
Output Modalities
Supported Functionality
mermaid
graph TDBase["Kwaipilot/KAT-Coder-V2.5-Dev<br/>Qwen3.5 MoE - 256 experts - ~69 GB bf16"]subgraph Build ["Build - RTX 5070 Ti, SM120"]REAP["REAP expert prune 50% 256 -> 128 experts + router-renorm fix"]Strip["strip vision tower + 333 untrained tensors"]Quant["NVFP4A16 quantize (weight-only, data-free, 82 s)"]endsubgraph HF ["Published formats"]A16["REAP-50-NVFP4A16 - 12.45 GiB (default, vLLM)"]W4A4["REAP-50-NVFP4-W4A4 (native FP4)"]GPTQ["REAP-50-NVFP4A16-GPTQ (null result, kept for transparency)"]GGUF["REAP-50-GGUF (Q4_K_M / Q5_K_M / Q6_K / Q8_0)"]BF16["REAP-50-bf16 (pruned source)"]endBench["A16 single draws - HumanEval+ 89.0% - MBPP+ 90.5% - SWE-bench Verified 52.0%"]Base --> REAP --> Strip --> Quant --> A16Strip --> BF16BF16 -. re-quant .-> W4A4BF16 -. re-quant .-> GPTQBF16 -. convert .-> GGUFA16 --> Bench
Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4-W4A4Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUFFull prune → quant → serve → evaluate pipeline: https://github.com/t-timms/kat-coder-nvfp4
Apache-2.0 (inherits from Kwaipilot/KAT-Coder-V2.5-Dev). Pruning via REAP
(github.com/CerebrasResearch/reap, with a router-renormalization fix).