LLM EXPLORER 56,604 MODELS INDEXED

Blossom V6.4 27B 9bit AWQ by McG-221

By McG-221 · 153 downloads
HF Repo ↗ Copy URL

Blossom V6.4 27B 9bit AWQ is an open-source language model by McG-221. Features: 27b LLM, VRAM: 31.2GB, Quantized.

  8-bit   9bit   Awq Base model:azure99/blossom-v6.... Base model:quantized:azure99/b...   Conversational   En   Image-text-to-text   Mlx   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/McG-221/Blossom-V6.4-27B-9bit-AWQ 

Blossom V6.4 27B 9bit AWQ Parameters and Internals

LLM NameBlossom V6.4 27B 9bit AWQ
Repository 🤗https://huggingface.co/McG-221/Blossom-V6.4-27B-9bit-AWQ 
Base Model(s)  Azure99/Blossom-V6.4-27B   Azure99/Blossom-V6.4-27B
Model Size27b
Required VRAM31.2 GB
Updated2026-08-09
MaintainerMcG-221
Model Typeqwen3_5
Model Files  5.4 GB: 1-of-6   5.4 GB: 2-of-6   5.3 GB: 3-of-6   5.4 GB: 4-of-6   5.3 GB: 5-of-6   4.4 GB: 6-of-6
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq|9bit
Model ArchitectureQwen3_5ForConditionalGeneration
Model Max Length262144
Transformers Version5.6.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Blossom V6.4 27B 9bit AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B AWQ 4bit0K / 18.7 GB672803
Qwen3.6 27B AWQ INT40K / 20.4 GB2563390103
Qwen3.6 27B AWQ0K / 22 GB66892424
Qwen3.6 27B AWQ BF16 INT40K / 28.3 GB41917141
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Qwen3.6 27B 4bit0K / 16 GB4367249
...inkingCap Qwen3.6 27B Mlx 6Bit0K / 21.8 GB34746
...kingCap Qwen3.6 27B OptiQ 4bit0K / 18.7 GB23553
Qwen3.5 27B OptiQ 4bit0K / 18.6 GB72693
Qwen3.6 27B 8bit0K / 29.4 GB479018
Note: green Score (e.g. "73.2") means that the model is better than McG-221/Blossom-V6.4-27B-9bit-AWQ.