← CanIRunLocal · All hardware · All models
No. Clef 27B (Cloudflare, decision) does not fit on RTX 3060 Ti 8GB: Q4_K_M needs 22.3 GB and 7.5 GB is usable.
Hardware: RTX 3060 Ti 8GB · Model: Clef 27B (Cloudflare, decision)
RTX 3060 Ti 8GB has 8 GB of VRAM and 448 GB/s of memory bandwidth. RTX 3070 8GB has the same memory and bandwidth, so the fit numbers match; this page is RTX 3060 Ti 8GB. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 7.5 GB. Partial offload may also use 60% of that system RAM. Clef 27B (Cloudflare, decision) (27B, Cloudflare) at Q4_K_M is a 20 GB download and needs 22.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 20 GB |
| Memory needed | 22.3 GB |
| Usable fast memory | 7.5 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run clef:27b-q4_K_M |
Smallest hardware that runs it: RTX 4060 Ti 16GB at Q4_K_M (partial offload (slower), 22.3 GB needed, 15.5 GB usable, about 4 tok/s (estimate)). Can a RTX 4060 Ti 16GB run Clef 27B (Cloudflare, decision)?
A smaller Cloudflare model that fits this hardware: Clef-Flash 9B (Cloudflare, decision) at Q8_0 (partial offload (slower), 12.4 GB). Can a RTX 3060 Ti 8GB run Clef-Flash 9B (Cloudflare, decision)?
Open RTX 3060 Ti 8GB in the checkerEstimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt