Can I run GLM-5.3-Flash-GGUF on an NVIDIA B200?
Yes
Its UD-IQ3_XXS file (120 GB) fits in the 162 GB an NVIDIA B200 can use, with room for an unknown amount of context.
Full analysis of GLM-5.3-Flash-GGUF
Everything that runs on NVIDIA B200
Get the UD-IQ3_XXS file on Hugging Face
llama-server -hf unsloth/GLM-5.3-Flash-GGUF:UD-IQ3_XXSFiles and context on NVIDIA B200
Each file of GLM-5.3-Flash-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.
| File | Size | On NVIDIA B200 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 642 GB | Doesn't fit | — | — |
| Q8_0 | 341 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 292 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 240 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 200 GB | Doesn't fit | — | — |
| UD-IQ4_XS | 157 GB | Doesn't fit | — | — |
| UD-Q3_K_XL | 148 GB | Doesn't fit | — | — |
| UD-IQ3_XXS | 120 GB | Fits | not known | not known |
| UD-Q2_K_XL | 109 GB | Fits | not known | not known |
| UD-IQ2_XXS | 102 GB | Fits | not known | not known |
| UD-IQ1_M | 97.6 GB | Fits | not known | not known |
| UD-IQ1_S | 93.1 GB | Fits | not known | not known |