LLM EXPLORER 61,755 MODELS INDEXED

Qwen3.6 27B OBLITERATED MLX 4bit by mlx-community

By mlx-community · 646 downloads
HF Repo ↗ Copy URL

Qwen3.6 27B OBLITERATED MLX 4bit is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 15.1GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.26.

  4-bit   4bit Base model:obliteratus/qwen3.6... Base model:quantized:obliterat...   Conversational   En   Mlx   Mlx-lm   Quantized   Qwen3   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.6-27B-OBLITERATED-MLX-4bit 

Qwen3.6 27B OBLITERATED MLX 4bit Parameters and Internals

LLM NameQwen3.6 27B OBLITERATED MLX 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3.6-27B-OBLITERATED-MLX-4bit 
Base Model(s)  OBLITERATUS/Qwen3.6-27B-OBLITERATED   OBLITERATUS/Qwen3.6-27B-OBLITERATED
Model Size27b
Required VRAM15.1 GB
Updated2026-07-24
Maintainermlx-community
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3_5ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.8.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size248320
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3.6 27B OBLITERATED MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...8 27B Obliterated E03 Bnb 4bit256K / 17.7 GB521
Qwen3.6 27B Bnb 4bit256K / 17.7 GB11940
Qwen3.8 27B OBLITERATED256K / 83.2 GB164950516
Qwen3.6 27B OBLITERATED256K / 53.6 GB15137184
JiRackDeltaNet 27b256K / 10.9 GB41540
Mnma Qwen3.8 27b Nvfp4256K / 18.8 GB52711
Qwen3.8 27B Code Tools Merged256K / 53.8 GB3183
Sharona Q27B R CodeSecurity V2256K / 53.8 GB10081
Qwen3.8 Whittle 16B256K / 2.4 GB17191
Barcenas Qwen3.8 27B Fable256K / 54.1 GB8775
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.6-27B-OBLITERATED-MLX-4bit.