LLM EXPLORER 59,278 MODELS INDEXED

Qwen3.6 35B A3B Escha W2 by r3lax

By r3lax · 329 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B Escha W2 is an open-source language model by r3lax. Features: 35b LLM, VRAM: 12.3GB, License: apache-2.0.

  2-bit   Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Code   Conversational   En   Eschamoe   Macos   Metal   Mixture-of-experts   Mlx   Model-index   Moe   Quantization   Qwen3   Qwen3 5 moe   Reasoning   Region:us   Safetensors   Sglang   Sharded   Tensorflow   Zml
Model Card on HF 🤗: https://huggingface.co/r3lax/Qwen3.6-35B-A3B-Escha-W2 

Qwen3.6 35B A3B Escha W2 Parameters and Internals

LLM NameQwen3.6 35B A3B Escha W2
Repository 🤗https://huggingface.co/r3lax/Qwen3.6-35B-A3B-Escha-W2 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM12.3 GB
Updated2026-08-23
Maintainerr3lax
Model Typeqwen3_5_moe
Model Files  0.0 GB   5.4 GB: 1-of-3   5.3 GB: 2-of-3   1.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B Escha W2

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Ornith 1.0 35B0K / 70.4 GB3192730505
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
Qwen3.6 35B A3B NVFP4 Fast0K / 23.6 GB46366198
Note: green Score (e.g. "73.2") means that the model is better than r3lax/Qwen3.6-35B-A3B-Escha-W2.