LLM EXPLORER 60,062 MODELS INDEXED

Qwen3.6 35B A3B RAM 25GB MLX by baa-ai

By baa-ai · 182 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B RAM 25GB MLX is an open-source language model by baa-ai. Features: 35b LLM, VRAM: 26.4GB, License: apache-2.0, LLM Explorer Score: 0.24.

  4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Conversational   En   Mixed-precision   Mlx   Moe   Quantized   Qwen   Qwen3   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/baa-ai/Qwen3.6-35B-A3B-RAM-25GB-MLX 

Qwen3.6 35B A3B RAM 25GB MLX Parameters and Internals

LLM NameQwen3.6 35B A3B RAM 25GB MLX
Repository 🤗https://huggingface.co/baa-ai/Qwen3.6-35B-A3B-RAM-25GB-MLX 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM26.4 GB
Updated2026-07-31
Maintainerbaa-ai
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-5   5.4 GB: 2-of-5   5.4 GB: 3-of-5   5.2 GB: 4-of-5   5.1 GB: 5-of-5
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B RAM 25GB MLX

Best Alternatives
Context / RAM
Downloads
Likes
Ornith 1.5 35B A3B NPU2256K /  GB1421
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Ornith 1.0 35B0K / 70.4 GB3045441504
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
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 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 baa-ai/Qwen3.6-35B-A3B-RAM-25GB-MLX.