LLM EXPLORER 63,892 MODELS INDEXED

DeepSeek V4 Pro Qwen3.5 9B Bf16 by mlx-community

By mlx-community · 837 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Pro Qwen3.5 9B Bf16 is an open-source language model by mlx-community. Features: 9b LLM, VRAM: 18.8GB, License: apache-2.0, LLM Explorer Score: 0.28.

  Agent Base model:finetune:jackrong/d... Base model:jackrong/deepseek-v...   Bf16   Coder   Conversational   En   Es   Function-calling   Image-text-to-text   Ja   Long-context   Mlx   Moe   Multimodal   Qwen3 5   Qwen3 5 moe   Qwen3 6   Region:us   Ru   Safetensors   Sharded   Tensorflow   Tool-use   Video   Vision   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-bf16 

DeepSeek V4 Pro Qwen3.5 9B Bf16 Parameters and Internals

LLM NameDeepSeek V4 Pro Qwen3.5 9B Bf16
Repository 🤗https://huggingface.co/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-bf16 
Model Nameunsloth/Qwen3.5-9B
Base Model(s)  Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B   Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
Model Size9b
Required VRAM18.8 GB
Updated2026-08-18
Maintainermlx-community
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-4   5.3 GB: 2-of-4   5.4 GB: 3-of-4   2.8 GB: 4-of-4
Supported Languagesen zh es ru ja
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Errorsreplace

Best Alternatives to DeepSeek V4 Pro Qwen3.5 9B Bf16

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 Distilled 9B NPU2256K /  GB32134
Clef Flash0K / 18.8 GB20670744
Qwen3.5 9B0K / 19.3 GB122077581799
MiMo V2.6 Distill Qwen 9B0K / 18.8 GB5705429
Qwable 9B Claude Fable 50K / 18.8 GB1088115
Ornith 1.0 9B0K / 18.8 GB897727555
LensVLM 9B0K / 18.8 GB1840258
Qwythos 9B Claude Mythos 5 1M0K / 18.8 GB37427906
Negentropy Claude Opus 4.7 9B0K / 18.8 GB6326
Qwen3.8 9B Distill0K / 19.3 GB5839148
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-bf16.