LLM EXPLORER 61,405 MODELS INDEXED

Qwythos 9B V2 OptiQ 4bit by mlx-community

By mlx-community · 419 downloads
HF Repo ↗ Copy URL

Qwythos 9B V2 OptiQ 4bit is an open-source language model by mlx-community. Features: 9b LLM, VRAM: 7.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.27.

  4-bit   4bit   8bit   Apple-silicon Base model:empero-ai/qwythos-9... Base model:quantized:empero-ai...   Conversational   Empero-ai   En   Ftpo   Image-text-to-text   Long-context   Mixed-precision   Mlx   Optiq   Quantized   Qwen3.5   Qwen3 5   Qwythos   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vision   Vision-language
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwythos-9B-v2-OptiQ-4bit 

Qwythos 9B V2 OptiQ 4bit Parameters and Internals

LLM NameQwythos 9B V2 OptiQ 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwythos-9B-v2-OptiQ-4bit 
Base Model(s)  Qwythos 9B V2   empero-ai/Qwythos-9B-v2
Model Size9b
Required VRAM7.1 GB
Updated2026-09-16
Maintainermlx-community
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   1.8 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwythos 9B V2 OptiQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 9B MLX 4bit0K / 5.9 GB5800124
Qwen3.5 9B MLX 8bit0K / 10.4 GB5504971
Ornith 1.5 9B MLX 4bit0K / 5 GB304318
Ornith 1.5 9B MLX 8bit0K / 9.5 GB26867
Qwen3.5 9B MLX 4bit0K / 5.9 GB22827151
Ornith 1.0 9B 4bit0K / 5.9 GB97919
Qwen3.5 9B 8bit0K / 10.4 GB4565217
Qwen3.5 9B 4bit Abliterated0K / 5.9 GB721
Qwen3.5 9B Theseus Q8 Hi Mlx0K / 10.9 GB1491
Qwen3.8 9B Mlx 4Bit0K / 5 GB5297
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwythos-9B-v2-OptiQ-4bit.