4-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 16.1 GB
Mac memory (est.)
24 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- Cloudflare/clef (quantized)
- Vendor
- Cloudflare
- Task
- Zero-shot classification
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 750 in the last 30 days · 2.7K all time · 13 likes
- Published
- 2026-10-01 · updated 2026-10-08 (1mo ago)
- Tags
- qwen3_5, clef, cloudflare, systemone, structured-output, classification, multimodal, custom-code, decision-model, eval-results
Other MLX builds of Cloudflare/clef
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| clef-4bit (this one) | 4-bit | ≈ 16.1 GB | 24 GB+ | 750 |
| clef-OptiQ-4bit | 4-bit | ≈ 16.1 GB | 24 GB+ | 279 |
| clef-8bit | 8-bit | ≈ 29.5 GB | 48 GB+ | 594 |