Can I run Cloudflare_clef-flash-GGUF on an RTX 5070?
Yes, just
Its Q8_0 file (9.68 GB) fits in the 10.8 GB an RTX 5070 can use, with room for ≈ 32K tokens of context.
Full analysis of Cloudflare_clef-flash-GGUF
Everything that runs on RTX 5070
Get the Q8_0 file on Hugging Face
ollama run hf.co/bartowski/Cloudflare_clef-flash-GGUF:Q8_0Files and context on RTX 5070
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 5070 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 18.2 GB | Doesn't fit | — | — |
| Q8_0 | 9.68 GB | Tight | 32K | 64K |
| Q6_K_L | 8.32 GB | Fits | 72K | 145K |
| Q6_K | 7.83 GB | Fits | 87K | 174K |
| Q5_K_M | 6.98 GB | Fits | 112K | 224K |
| Q4_K_L | 6.80 GB | Fits | 118K | 236K |
| Q5_K_S | 6.66 GB | Fits | 122K | 244K |
| Q4_1 | 6.07 GB | Fits | 139K | 256K |
| Q4_K_M | 6.04 GB | Fits | 140K | 256K |
| Q4_K_S | 5.73 GB | Fits | 150K | 256K |
| IQ4_NL | 5.63 GB | Fits | 152K | 256K |
| Q4_0 | 5.60 GB | Fits | 153K | 256K |
| IQ4_XS | 5.40 GB | Fits | 159K | 256K |
| Q3_K_L | 5.24 GB | Fits | 164K | 256K |
| Q3_K_M | 5.05 GB | Fits | 170K | 256K |
| IQ3_M | 4.85 GB | Fits | 176K | 256K |
| Q3_K_S | 4.80 GB | Fits | 177K | 256K |
| Q2_K | 4.19 GB | Fits | 195K | 256K |