LLM EXPLORER 59,278 MODELS INDEXED

Ornith 1.5 35B A3B AWQ INT4 by ulkaa

By ulkaa · 2008 downloads
HF Repo ↗ Copy URL

Ornith 1.5 35B A3B AWQ INT4 is an open-source language model by ulkaa. Features: 35b LLM, VRAM: 24.4GB, License: mit, Quantized, LLM Explorer Score: 0.34.

  4-bit   4bit   Awq Base model:ornith-ai/ornith-1.... Base model:quantized:ornith-ai...   Compressed-tensors   Conversational   Endpoints compatible   Image-text-to-text   Int4   Intel-xpu   Moe   Mtp   Multimodal   Ornith   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sglang   Sharded   Speculative-decoding   Tensorflow   W4a16
Model Card on HF 🤗: https://huggingface.co/ulkaa/Ornith-1.5-35B-A3B-AWQ-INT4 

Ornith 1.5 35B A3B AWQ INT4 Parameters and Internals

LLM NameOrnith 1.5 35B A3B AWQ INT4
Repository 🤗https://huggingface.co/ulkaa/Ornith-1.5-35B-A3B-AWQ-INT4 
Base Model(s)  ornith-ai/Ornith-1.5-35B-A3B   ornith-ai/Ornith-1.5-35B-A3B
Model Size35b
Required VRAM24.4 GB
Updated2026-08-22
Maintainerulkaa
Model Typeqwen3_5_moe
Model Files  20.0 GB: 1-of-2   4.4 GB: 2-of-2   1.7 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licensemit
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Ornith 1.5 35B A3B AWQ INT4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B AWQ0K / 25.5 GB102070932
Qwen3.6 35B A3B AWQ 4bit0K / 25 GB101078593
Qwen3.6 35B A3B MLX 4bit0K / 20.5 GB5131936
Qwen3.6 35B A3B MLX 6bit0K / 28.9 GB4785922
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB4735371
Qwen3.6 35B A3B UD MLX 4bit0K / 21.6 GB15720112
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Note: green Score (e.g. "73.2") means that the model is better than ulkaa/Ornith-1.5-35B-A3B-AWQ-INT4.