Cloudflare · 9.4B · Dense
Smaller Clef on Qwen 3.5 9B — the same typed decisions over text, images and video at a third of the size Check if your GPU or Mac can run Clef Flash locally — 5.3 GB min, 8.8 GB recommended.
2026-09256K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 3.5 GB | low | — |
| Q3_K_M | 3 | 4.7 GB | moderate | — |
| Q4_K_M | 4 | 5.3 GB | good | — |
| Q5_K_M | 5 | 6.5 GB | good | — |
| Q6_K | 6 | 7.7 GB | excellent | — |
| Q8_0 | 8 | 10.1 GB | excellent | — |
| F16 | 16 | 19.8 GB | lossless | — |
Can I run Clef Flash locally?
- Can I run Clef Flash locally?
- Clef Flash needs about 5.3 GB of memory at a minimum and 8.8 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Clef Flash need?
- At Q4_K_M, Clef Flash uses about 5.3 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.