Store › model › LLM
Ornith-1.0-9B-GGUF
by unsloth · source Hugging Face · updated 2026-07-18
mit5.3 GB~7 GB RAMsource aliveunlabeled
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:unsloth/Ornith-1.0-9B-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/unsloth/Ornith-1.0-9B-GGUF
- License: mit · text
- Requirements: about 7 GB of RAM, 5.3 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
ggufunslothqwen3_5_moetext-generationendpoints_compatibleconversational
Numbers
- 427,844 downloads on Hugging Face
- 63 likes
- license mit
- 5.3 GB for Ornith-1.0-9B-Q4_K_M.gguf
- 130,156 stars on ggml-org/llama.cpp
- 2,528 open issues and PRs
- last release v0.5.0 on 2026-09-23
- 327,838 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-02 20:53 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
Ornith-1.0-9B-BF16.gguf | BF16 | 17 GB |
Ornith-1.0-9B-IQ4_NL.gguf | IQ4_NL | 5.1 GB |
Ornith-1.0-9B-IQ4_XS.gguf | IQ4_XS | 4.9 GB |
Ornith-1.0-9B-Q3_K_M.gguf | Q3_K_M | 4.4 GB |
Ornith-1.0-9B-Q3_K_S.gguf | Q3_K_S | 4.0 GB |
Ornith-1.0-9B-Q4_0.gguf | Q4_0 | 5.0 GB |
Ornith-1.0-9B-Q4_1.gguf | Q4_1 | 5.5 GB |
Ornith-1.0-9B-Q4_K_M.gguf | Q4_K_M | 5.3 GB |
Ornith-1.0-9B-Q4_K_S.gguf | Q4_K_S | 5.1 GB |
Ornith-1.0-9B-Q5_K_M.gguf | Q5_K_M | 6.1 GB |
Ornith-1.0-9B-Q5_K_S.gguf | Q5_K_S | 5.9 GB |
Ornith-1.0-9B-Q6_K.gguf | Q6_K | 7.0 GB |
Ornith-1.0-9B-Q8_0.gguf | Q8_0 | 8.9 GB |
Ornith-1.0-9B-UD-IQ2_M.gguf | IQ2_M | 3.6 GB |
Ornith-1.0-9B-UD-IQ3_XXS.gguf | IQ3_XXS | 3.9 GB |
Ornith-1.0-9B-UD-Q2_K_XL.gguf | Q2_K_XL | 4.0 GB |
Ornith-1.0-9B-UD-Q3_K_XL.gguf | Q3_K_XL | 4.8 GB |
Ornith-1.0-9B-UD-Q4_K_XL.gguf | Q4_K_XL | 5.6 GB |
Ornith-1.0-9B-UD-Q5_K_XL.gguf | Q5_K_XL | 6.2 GB |
Ornith-1.0-9B-UD-Q6_K_XL.gguf | Q6_K_XL | 8.2 GB |
Ornith-1.0-9B-UD-Q8_K_XL.gguf | Q8_K_XL | 12 GB |
mmproj-BF16.gguf | BF16 | 879 MB |
mmproj-F16.gguf | F16 | 876 MB |
mmproj-F32.gguf | F32 | 1.7 GB |
From the source README
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.
Ornith-1.0-9B
Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.
Highlights:
- State-of-the-Art Coding Agents: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.
- Self-Improving Training Framework: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions.
- Licence: MIT licensed, globally accessible, and free from regional limitations.
Ornith 1.0 9B
This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment.
Benchmarks
Ornith-1.0-9B
Qwen3.5-9B
Qwen3.5-35B
Gemma4-12B
Gemma4-31B
Agentic Coding
Terminal-Bench 2.1 (Terminus-2)
43.1
21.3
41.4
21
42.1
Terminal-Bench 2.1 (Claude Code)
40.6
18.9
38.9
-
-
Card id model:hf:unsloth/Ornith-1.0-9B-GGUF · collected 2026-10-02 20:53 UTC · JSON