LLM EXPLORER 60,702 MODELS INDEXED

Grug V1.1 Qwen 3.8 27B MLX 4bit by pgmharikrishnan

By pgmharikrishnan · 38 downloads
HF Repo ↗ Copy URL

Grug V1.1 Qwen 3.8 27B MLX 4bit is an open-source language model by pgmharikrishnan. Features: 27b LLM, VRAM: 15.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

  4-bit   4bit   Agent   Apple-silicon Base model:procreations/grug-v... Base model:quantized:procreati...   Code   Conversational   En   Mlx   Mlx-my-repo   Quantized   Qwen   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/pgmharikrishnan/grug-v1.1-qwen-3.8-27b-MLX-4bit 

Grug V1.1 Qwen 3.8 27B MLX 4bit Parameters and Internals

LLM NameGrug V1.1 Qwen 3.8 27B MLX 4bit
Repository 🤗https://huggingface.co/pgmharikrishnan/grug-v1.1-qwen-3.8-27b-MLX-4bit 
Base Model(s)  ProCreations/grug-v1.1-qwen-3.8-27b   ProCreations/grug-v1.1-qwen-3.8-27b
Model Size27b
Required VRAM15.1 GB
Updated2026-09-08
Maintainerpgmharikrishnan
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_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.15.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Grug V1.1 Qwen 3.8 27B MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B 8bit0K / 29.4 GB1389233
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
...en3.8 27B Abliterated MLX 4bit0K / 16 GB166426
Qwen3.8 27B MLX 4bit0K / 16 GB1971210
Qwen3.8 27B 4bit0K / 16 GB605527
Note: green Score (e.g. "73.2") means that the model is better than pgmharikrishnan/grug-v1.1-qwen-3.8-27b-MLX-4bit.