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

Can I run POCKET-35B-GGUF on an RTX 4080?

Yes, just

Its Q2_K file (12.9 GB) fits in the 14.4 GB an RTX 4080 can use, with room for ≈ 67K tokens of context. That file is under 3 bits per weight, so expect noticeably lower quality.

Full analysis of POCKET-35B-GGUF Everything that runs on RTX 4080 Get the Q2_K file on Hugging Face
ollama run hf.co/FINAL-Bench/POCKET-35B-GGUF:Q2_K

Files and context on RTX 4080

Each file of POCKET-35B-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 4080 Context (16-bit)Context (8-bit)
Q4_K_M21.2 GBDoesn't fit——
Q3_K_M16.8 GBDoesn't fit——
Q2_K12.9 GBTight67K133K
IQ1_M8.24 GBFits256K256K

POCKET-35B-GGUF on other hardware

Popular models that run on RTX 4080

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.