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
ornith-ai/Ornith-1.5-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
mermaid
graph TDBase["ornith-ai/Ornith-1.5-35B-A3B<br/>qwen3_5_moe - 256 experts - MTP head - ~65 GB bf16 - MIT"]subgraph Build ["Build - RTX 5070 Ti, SM120"]REAP["REAP expert prune 50% 256 -> 128"]MTP["strip MTP head (1 -> 0, reload-verified)"]StripV["strip vision tower (333 tensors)"]Quant["GPTQ-NVFP4A16 quantize (~5.5 h, 12.47 GiB)"]endsubgraph HF ["Published formats"]A16["REAP-50-NVFP4A16 - 12.47 GiB (vLLM)"]GGUF["REAP-50-GGUF (Q4_K_M / Q5_K_M / Q6_K / Q8_0)"]BF16["REAP-50-bf16 (pruned source)"]endBench["HumanEval+ 84.2% - MBPP+ 89.2% - SWE-bench Verified 44.0%"]Base --> REAP --> MTP --> StripV --> Quant --> A16StripV --> BF16BF16 -. convert .-> GGUFA16 --> Bench
Ttimms/Ornith-1.5-35B-A3B-REAP-50-NVFP4A16Ttimms/Ornith-1.5-35B-A3B-REAP-50-GGUFFull prune → strip → quant → serve → evaluate pipeline, with the bugs found and fixed along the way: https://github.com/t-timms/ornith-nvfp4
MIT (inherits from ornith-ai/Ornith-1.5-35B-A3B). Pruning via REAP
(github.com/CerebrasResearch/reap).