LLM EXPLORER 59,516 MODELS INDEXED

Ornith 1.5 35B A3B OQ8e Fixed Mtp by pyros-vault

By pyros-vault · 214 downloads
HF Repo ↗ Copy URL

Ornith 1.5 35B A3B OQ8e Fixed Mtp is an open-source language model by pyros-vault. Features: 35b LLM, VRAM: 38.4GB, License: apache-2.0, LLM Explorer Score: 0.31.

  8-bit Base model:quantized:shisa-ai/... Base model:shisa-ai/ornith-1.5...   Conversational   Image-text-to-text   Mlx   Moe   Mtp   Multimodal   Omlx   Oq   Quantized   Qwen3.6   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/pyros-vault/Ornith-1.5-35B-A3B-oQ8e-fixed-mtp 

Ornith 1.5 35B A3B OQ8e Fixed Mtp Parameters and Internals

LLM NameOrnith 1.5 35B A3B OQ8e Fixed Mtp
Repository 🤗https://huggingface.co/pyros-vault/Ornith-1.5-35B-A3B-oQ8e-fixed-mtp 
Base Model(s)  shisa-ai/Ornith-1.5-35B-A3B-MTP   shisa-ai/Ornith-1.5-35B-A3B-MTP
Model Size35b
Required VRAM38.4 GB
Updated2026-08-25
Maintainerpyros-vault
Model Typeqwen3_5_moe
Model Files  5.2 GB: 1-of-8   5.1 GB: 2-of-8   5.1 GB: 3-of-8   5.1 GB: 4-of-8   5.1 GB: 5-of-8   5.1 GB: 6-of-8   5.1 GB: 7-of-8   2.6 GB: 8-of-8
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Ornith 1.5 35B A3B OQ8e Fixed Mtp

Best Alternatives
Context / RAM
Downloads
Likes
Ornith 1.5 35B A3B NPU2256K /  GB1181
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Ornith 1.0 35B0K / 70.4 GB3323741505
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.5 35B A3B0K / 72.1 GB1713201
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Ornith 1.5 35B A3B NVFP40K / 23.4 GB2423829
Note: green Score (e.g. "73.2") means that the model is better than pyros-vault/Ornith-1.5-35B-A3B-oQ8e-fixed-mtp.