LLM EXPLORER 63,287 MODELS INDEXED

Ornith 1.0 35B MTPLX by wang-yang

By wang-yang · 25034 downloads
HF Repo ↗ Copy URL

Ornith 1.0 35B MTPLX is an open-source language model by wang-yang. Features: 35b LLM, VRAM: 19.5GB, License: mit, LLM Explorer Score: 0.32.

  4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-35b-a3...   Conversational   En   Mlx   Moe   Mtp   Mtplx   Multi-token-prediction   Qwen35moe   Qwen3 5 moe   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow
Model Card on HF 🤗: https://huggingface.co/wang-yang/Ornith-1.0-35B-MTPLX 

Ornith 1.0 35B MTPLX Parameters and Internals

LLM NameOrnith 1.0 35B MTPLX
Repository 🤗https://huggingface.co/wang-yang/Ornith-1.0-35B-MTPLX 
Base Model(s)  deepreinforce-ai/Ornith-1.0-35B   Qwen/Qwen3.5-35B-A3B   deepreinforce-ai/Ornith-1.0-35B   Qwen/Qwen3.5-35B-A3B
Model Size35b
Required VRAM19.5 GB
Updated2026-07-31
Maintainerwang-yang
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.4 GB: 3-of-4   3.4 GB: 4-of-4   1.7 GB
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licensemit
Model Max Length262144
Transformers Version5.8.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Ornith 1.0 35B MTPLX

Best Alternatives
Context / RAM
Downloads
Likes
....5 35B A3B Sceptic V3 1M W4A161024K / 26.1 GB2230
...AgentWorld 35B A3B Abliterated256K / 69.2 GB96218
Ornith 1.5 35B A3B NPU2256K /  GB861
Qwen3.6 35B A3B NPU2256K /  GB930
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.0 35B0K / 70.4 GB1418212506
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Note: green Score (e.g. "73.2") means that the model is better than wang-yang/Ornith-1.0-35B-MTPLX.