What are the hardware requirements for DeepSeek V4 Pro Qwen3.5 9B?

DeepSeek V4 Pro Qwen3.5 9B requires approximately 19.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepSeek V4 Pro Qwen3.5 9B and how large is it?

DeepSeek V4 Pro Qwen3.5 9B is developed by Jackrong, a model with 9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate DeepSeek V4 Pro Qwen3.5 9B?

DeepSeek V4 Pro Qwen3.5 9B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepSeek V4 Pro Qwen3.5 9B by Jackrong — VRAM 19.3GB

Name: DeepSeek V4 Pro Qwen3.5 9B
Author: Jackrong

DeepSeek V4 Pro Qwen3.5 9B is an open-source language model by Jackrong. Features: 9b LLM, VRAM: 19.3GB, License: apache-2.0, LLM Explorer Score: 0.24.

Base model:finetune:unsloth/qw... Base model:unsloth/qwen3.5-9b Conversational Dataset:jackrong/deepseek-v4-d... Dataset:jackrong/deepseek-v4-p... Deepseek Distillation En Endpoints compatible Es Function-calling Gspo Image-text-to-text Ja Ko Math Mtp Qwen3 5 Reasoning Region:us Rl Ru Safetensors Sft Sharded Stem Tensorflow Tool-use Unsloth Zh

Model Card on HF 🤗: https://huggingface.co/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B

DeepSeek V4 Pro Qwen3.5 9B Parameters and Internals

LLM Name	DeepSeek V4 Pro Qwen3.5 9B
Repository 🤗	https://huggingface.co/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
Model Name	unsloth/Qwen3.5-9B
Base Model(s)	unsloth/Qwen3.5-9B unsloth/Qwen3.5-9B
Model Size	9b
Required VRAM	19.3 GB
Updated	2026-08-08
Maintainer	Jackrong
Model Type	qwen3_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 Languages	en zh ko ja es ru
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|vision_pad\|>
Torch Data Type	bfloat16
Errors	replace

Rank the DeepSeek V4 Pro Qwen3.5 9B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the DeepSeek V4 Pro Qwen3.5 9B

Model	Likes	Downloads	VRAM
...eepSeek V4 Pro Qwen3.5 9B 4bit	1	544	5 GB

Best Alternatives to DeepSeek V4 Pro Qwen3.5 9B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Distilled 9B NPU2	256K / GB	3213	4
Clef Flash	0K / 18.8 GB	20670	744
Qwen3.5 9B	0K / 19.3 GB	12207758	1799
MiMo V2.6 Distill Qwen 9B	0K / 18.8 GB	5705	429
Qwable 9B Claude Fable 5	0K / 18.8 GB	1088	115
Ornith 1.0 9B	0K / 18.8 GB	897727	555
LensVLM 9B	0K / 18.8 GB	1840	258
Qwythos 9B Claude Mythos 5 1M	0K / 18.8 GB	37427	906
Negentropy Claude Opus 4.7 9B	0K / 18.8 GB	63	26
Qwen3.8 9B Distill	0K / 19.3 GB	5839	148

Note: green Score (e.g. "73.2") means that the model is better than Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B.