unsloth / text-generation updated 2 months ago

Ornith-1.0-35B-GGUF

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

Params
Context
Downloads 30d
183 K
Likes
150
Commercial use: allowed mit Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 49 days
▲ 11 K in the last 30 days (5.6%)
255 K183 K
Aug 4Aug 20Sep 5Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Ornith-1.0-35B-UD-IQ1_S.gguf IQ1_S 10.5 GB 12.1 GB ✅ Runs comfortably
Ornith-1.0-35B-UD-IQ1_M.gguf IQ1_M 11.0 GB 12.6 GB ✅ Runs comfortably
Ornith-1.0-35B-UD-IQ2_XXS.gguf IQ2_XXS 11.5 GB 13.1 GB ✅ Runs comfortably
Ornith-1.0-35B-UD-IQ2_M.gguf IQ2_M 11.6 GB 13.2 GB ✅ Runs comfortably
Ornith-1.0-35B-UD-IQ3_XXS.gguf IQ3_XXS 13.7 GB 15.6 GB ✅ Runs comfortably
Ornith-1.0-35B-UD-IQ3_S.gguf IQ3_S 15.0 GB 17.0 GB ✅ Runs comfortably
Ornith-1.0-35B-Q8_0.gguf Q8_0 36.9 GB 41.1 GB ❌ Won’t fit
Ornith-1.0-35B-BF16-00001-of-00002.gguf GGUF 49.8 GB 55.3 GB ❌ Won’t fit
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · GGUF
$ ollama run ornith-1-0-35b-gguf-unsloth

# pin the quantization explicitly
$ ollama run ornith-1-0-35b-gguf-unsloth-gguf
est. VRAM 55.3 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
mit
First seen on the Hub
2026-07-17
Base model
Ornith-1.0-35B
Training datasets
undisclosed
Added to our catalog
2026-08-04

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-generation model