Can I run Cloudflare_clef-flash-GGUF on an RTX 4060?
Yes, just
Its Q5_K_M file (6.98 GB) fits in the 7.20 GB an RTX 4060 can use, with room for ≈ 5K tokens of context.
Full analysis of Cloudflare_clef-flash-GGUF
Everything that runs on RTX 4060
Get the Q5_K_M file on Hugging Face
ollama run hf.co/bartowski/Cloudflare_clef-flash-GGUF:Q5_K_MFiles and context on RTX 4060
Each file of Cloudflare_clef-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 RTX 4060 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 18.2 GB | Doesn't fit | — | — |
| Q8_0 | 9.68 GB | Doesn't fit | — | — |
| Q6_K_L | 8.32 GB | Doesn't fit | — | — |
| Q6_K | 7.83 GB | Doesn't fit | — | — |
| Q5_K_M | 6.98 GB | Tight | 5K | 10K |
| Q4_K_L | 6.80 GB | Tight | 11K | 21K |
| Q5_K_S | 6.66 GB | Tight | 15K | 29K |
| Q4_1 | 6.07 GB | Tight | 32K | 64K |
| Q4_K_M | 6.04 GB | Tight | 33K | 66K |
| Q4_K_S | 5.73 GB | Fits | 42K | 85K |
| IQ4_NL | 5.63 GB | Fits | 45K | 90K |
| Q4_0 | 5.60 GB | Fits | 46K | 92K |
| IQ4_XS | 5.40 GB | Fits | 52K | 104K |
| Q3_K_L | 5.24 GB | Fits | 57K | 114K |
| Q3_K_M | 5.05 GB | Fits | 63K | 125K |
| IQ3_M | 4.85 GB | Fits | 68K | 137K |
| Q3_K_S | 4.80 GB | Fits | 70K | 140K |
| Q2_K | 4.19 GB | Fits | 88K | 176K |