LLM EXPLORER 60,587 MODELS INDEXED

Qwen3.5 9B DeepSeek V4 Flash by Jackrong

By Jackrong · 845 downloads
HF Repo ↗ Copy URL

Qwen3.5 9B DeepSeek V4 Flash is an open-source language model by Jackrong. Features: 9b LLM, VRAM: 19.3GB, License: apache-2.0, LLM Explorer Score: 0.27.

  Arxiv:2604.06628   Agent Base model:finetune:unsloth/qw...   Base model:unsloth/qwen3.5-9b   Chain-of-thought   Conversational Dataset:jackrong/deepseek-v4-d...   Deepseek   Deepseek-v4   Distillation   Efficient-inference   En   Endpoints compatible   Es   Image-text-to-text   Ja   Ko   Long-cot   Multilingual   Qwen3 5   Reasoning   Region:us   Ru   Safetensors   Sft   Sharded   Tensorflow   Unsloth   Zh
Model Card on HF 🤗: https://huggingface.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash 

Qwen3.5 9B DeepSeek V4 Flash Parameters and Internals

LLM NameQwen3.5 9B DeepSeek V4 Flash
Repository 🤗https://huggingface.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash 
Model NameUnsloth/Qwen3.5-9B
Base Model(s)  unsloth/Qwen3.5-9B   unsloth/Qwen3.5-9B
Model Size9b
Required VRAM19.3 GB
Updated2026-08-09
MaintainerJackrong
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-4   5.3 GB: 2-of-4   5.4 GB: 3-of-4   3.3 GB: 4-of-4
Supported Languagesen zh ko ja es ru
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Tokenizer ClassTokenizersBackend
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3.5 9B DeepSeek V4 Flash

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 Distilled 9B NPU2256K /  GB27263
Qwen3.5 9B0K / 19.3 GB122077581799
Ornith 1.0 9B0K / 18.8 GB1632497541
Qwable 9B Claude Fable 50K / 18.8 GB1088115
Qwythos 9B Claude Mythos 5 1M0K / 18.8 GB37427906
WeMM Embedding 9B0K / 18.8 GB2618105
Qwen3.8 9B Distill0K / 19.3 GB5839148
Negentropy Claude Opus 4.7 9B0K / 18.8 GB6326
Ornith 1.5 9B0K / 18.9 GB1324120
Qwythos 9B V20K / 19.3 GB19208156
Note: green Score (e.g. "73.2") means that the model is better than Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash.