LLM EXPLORER 60,277 MODELS INDEXED

Qwen3.6 35B Rust.mlx by jedisct1

By jedisct1 · 386 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B Rust.mlx is an open-source language model by jedisct1. Features: 35b LLM, VRAM: 37.1GB, License: other, Quantized, LLM Explorer Score: 0.25.

  8-bit Base model:adapter:brooooookly... Base model:brooooooklyn/qwen3....   Code-generation   Conversational   Dataset:jedisct1/rust   En   Finetuned   Lora   Mlx   Moe   Q8   Quantized   Qwen3 5 moe   Region:us   Rust   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/jedisct1/Qwen3.6-35B-rust.mlx 

Qwen3.6 35B Rust.mlx Parameters and Internals

LLM NameQwen3.6 35B Rust.mlx
Repository 🤗https://huggingface.co/jedisct1/Qwen3.6-35B-rust.mlx 
Base Model(s)  Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx   Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx
Model Size35b
Required VRAM37.1 GB
Updated2026-08-08
Maintainerjedisct1
Model Typeqwen3_5_moe
Model Files  5.4 GB: 1-of-8   5.1 GB: 2-of-8   5.4 GB: 3-of-8   5.1 GB: 4-of-8   5.1 GB: 5-of-8   5.1 GB: 6-of-8   5.4 GB: 7-of-8   0.5 GB: 8-of-8
Supported Languagesen
Quantization Typeq8
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
LoRA ModelYes
Errorsreplace

Best Alternatives to Qwen3.6 35B Rust.mlx

Best Alternatives
Context / RAM
Downloads
Likes
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
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Qwen3.6 35B A3B 5bit0K / 24.7 GB16285
Ornith 1.5 35B A3B MLX 6bit0K / 28 GB342096
Note: green Score (e.g. "73.2") means that the model is better than jedisct1/Qwen3.6-35B-rust.mlx.