LLM EXPLORER 67,390 MODELS INDEXED

Qwen3.8 27B RFT V1 Mlx 4bit by ghostrider0470

By ghostrider0470 · 147 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B RFT V1 Mlx 4bit is an open-source language model by ghostrider0470. Features: 27b LLM, VRAM: 15.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  4-bit   4bit Base model:ghostrider0470/qwen... Base model:quantized:ghostride...   Conversational   Mlx   Quantized   Qwen   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ghostrider0470/Qwen3.8-27B-RFT-v1-mlx-4bit 

Qwen3.8 27B RFT V1 Mlx 4bit Parameters and Internals

LLM NameQwen3.8 27B RFT V1 Mlx 4bit
Repository 🤗https://huggingface.co/ghostrider0470/Qwen3.8-27B-RFT-v1-mlx-4bit 
Base Model(s)  ghostrider0470/Qwen3.8-27B-RFT-v1   ghostrider0470/Qwen3.8-27B-RFT-v1
Model Size27b
Required VRAM15.1 GB
Updated2026-11-13
Maintainerghostrider0470
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   4.5 GB: 3-of-3
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen3_5Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B RFT V1 Mlx 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Qwopus3.8 27B Coder Flash 8bit0K / 29.4 GB4453
Qwopus3.8 27B Coder Flash 4bit0K / 16 GB3742
Qwopus3.8 27B Coder Flash 6bit0K / 22.7 GB3322
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B MLX 5bit0K / 19.5 GB46750442
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
Note: green Score (e.g. "73.2") means that the model is better than ghostrider0470/Qwen3.8-27B-RFT-v1-mlx-4bit.