Model Anatomy See what's inside open-weight AI models

Can I run DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF on an RTX 3090?

Yes

Its Q8_0 file (9.79 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 256K tokens of context.

Full analysis of DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF Everything that runs on RTX 3090 Get the Q8_0 file on Hugging Face
ollama run hf.co/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF:Q8_0

Files and context on RTX 3090

Each file of DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn RTX 3090 Context (16-bit)Context (8-bit)
Q8_09.79 GBFits256K256K
Q6_K7.56 GBFits256K256K
Q5_K_M6.64 GBFits256K256K
Q5_K_S6.47 GBFits256K256K
Q4_K_M5.78 GBFits256K256K
Q4_K_S5.49 GBFits256K256K
IQ4_XS5.36 GBFits256K256K

DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF on other hardware

Popular models that run on RTX 3090

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.