8-bit Open on Hugging Face
Parameters
32B
Weights (est.)
≈ 34.8 GB
Mac memory (est.)
48 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-omni (quantized)
- Vendor
- Cloudflare
- Task
- Zero-shot classification
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 274 in the last 30 days · 568 all time · 3 likes
- Published
- 2026-10-09 · updated 2026-10-09 (1mo ago)
- Tags
- qwen3_omni_moe, clef, cloudflare, systemone, structured-output, classification, multimodal, audio, video, custom-code, decision-model
Other MLX builds of Cloudflare/clef-omni
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| clef-omni-4bit | 4-bit | ≈ 19.5 GB | 24 GB+ | 534 |
| clef-omni-8bit (this one) | 8-bit | ≈ 34.8 GB | 48 GB+ | 274 |