Can I run glm-4-9b-chat-IMat-GGUF on an RTX 5060 Ti 16 GB?
Yes
Its Q8_0 file (9.99 GB) fits in the 14.4 GB an RTX 5060 Ti 16 GB can use, with room for ≈ 105K tokens of context.
Full analysis of glm-4-9b-chat-IMat-GGUF
Everything that runs on RTX 5060 Ti 16 GB
Get the Q8_0 file on Hugging Face
ollama run hf.co/legraphista/glm-4-9b-chat-IMat-GGUF:Q8_0Files and context on RTX 5060 Ti 16 GB
Each file of glm-4-9b-chat-IMat-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 RTX 5060 Ti 16 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 18.8 GB | Doesn't fit | — | — |
| glm-4-9b-chat.FP16 | 18.8 GB | Doesn't fit | — | — |
| Q8_0 | 9.99 GB | Fits | 105K | 128K |
| Q6_K | 8.26 GB | Fits | 128K | 128K |
| Q5_K | 7.14 GB | Fits | 128K | 128K |
| Q5_K_S | 6.69 GB | Fits | 128K | 128K |
| Q4_K | 6.25 GB | Fits | 128K | 128K |
| Q4_K_S | 5.75 GB | Fits | 128K | 128K |
| IQ4_NL | 5.46 GB | Fits | 128K | 128K |
| Q3_K_L | 5.28 GB | Fits | 128K | 128K |
| IQ4_XS | 5.25 GB | Fits | 128K | 128K |
| Q3_K | 5.06 GB | Fits | 128K | 128K |
| IQ3_M | 4.81 GB | Fits | 128K | 128K |
| IQ3_S | 4.59 GB | Fits | 128K | 128K |
| Q3_K_S | 4.59 GB | Fits | 128K | 128K |
| IQ3_XS | 4.43 GB | Fits | 128K | 128K |
| IQ3_XXS | 4.26 GB | Fits | 128K | 128K |
| Q2_K | 3.99 GB | Fits | 128K | 128K |
| Q2_K_S | 3.96 GB | Fits | 128K | 128K |
| IQ2_M | 3.93 GB | Fits | 128K | 128K |
| IQ2_S | 3.77 GB | Fits | 128K | 128K |
| IQ2_XS | 3.61 GB | Fits | 128K | 128K |
| IQ2_XXS | 3.43 GB | Fits | 128K | 128K |
| IQ1_M | 3.22 GB | Fits | 128K | 128K |
| IQ1_S | 3.10 GB | Fits | 128K | 128K |