LLM EXPLORER 60,645 MODELS INDEXED

Qwen3.6 35B A3B PRISM NVFP4 by Ex0bit

By Ex0bit · 29506 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B PRISM NVFP4 is an open-source language model by Ex0bit. Features: 35b LLM, VRAM: 1.7GB, License: apache-2.0, LLM Explorer Score: 0.31.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Compressed-tensors   Conversational   Moe   Nvfp4   Qwen3.5   Qwen3 5 moe   Region:us   Safetensors   Vllm   W4a4
Model Card on HF 🤗: https://huggingface.co/Ex0bit/Qwen3.6-35B-A3B-PRISM-NVFP4 

Qwen3.6 35B A3B PRISM NVFP4 Parameters and Internals

LLM NameQwen3.6 35B A3B PRISM NVFP4
Repository 🤗https://huggingface.co/Ex0bit/Qwen3.6-35B-A3B-PRISM-NVFP4 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM1.7 GB
Updated2026-08-06
MaintainerEx0bit
Model Typeqwen3_5_moe
Model Files  23.4 GB   1.7 GB
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.5.4
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B PRISM NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
Ornith 1.5 35B A3B NPU2256K /  GB1781
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Ornith 1.0 35B0K / 70.4 GB2983134506
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Ornith 1.5 35B A3B0K / 72.1 GB1713201
Qwen3.6 35B A3B NVFP4 Fast0K / 23.6 GB46366198
Note: green Score (e.g. "73.2") means that the model is better than Ex0bit/Qwen3.6-35B-A3B-PRISM-NVFP4.