Store › model › LLM
Ornith-1.5-9B-GGUF
by ornith-ai · source Hugging Face · updated 2026-08-24
mit5.4 GB~7 GB RAMsource aliveunlabeled
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
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:ornith-ai/Ornith-1.5-9B-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/ornith-ai/Ornith-1.5-9B-GGUF
- License: mit · text
- Requirements: about 7 GB of RAM, 5.4 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:
transformersgguftext-generationendpoints_compatibleconversational
Numbers
- 5,051,736 downloads on Hugging Face
- 479 likes
- license mit
- 5.4 GB for Ornith-1.5-9B-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 20:54 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-1.5-9B-BF16.gguf | BF16 | 17 GB |
Ornith-1.5-9B-Q4_K_M.gguf | Q4_K_M | 5.4 GB |
Ornith-1.5-9B-Q5_K_M.gguf | Q5_K_M | 6.2 GB |
Ornith-1.5-9B-Q6_K.gguf | Q6_K | 7.0 GB |
Ornith-1.5-9B-Q8_0.gguf | Q8_0 | 9.1 GB |
mmproj-Ornith-1.5-9B-BF16.gguf | BF16 | 879 MB |
From the source README
Ornith-1.5-9B
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For more details on the task, harness, and rollout reward design, please refer to our blog.
Ornith 1.5 9B
This model card documents Ornith-1.5-9B, the most lightweight member of the Ornith-1.5 family — a 9B dense model designed for efficient single-GPU deployment, and edge-deployable on mobile devices via its quantized Ornith-1.5-9B-Mobile variant.
Benchmarks
Ornith-1.5-9B
Ornith-1.0-9B
Qwen3.5-9B
Qwen3.6-35B-A3B
Gemma-4-31B
Coding
Terminal-Bench 2.1 (Terminus-2)
46.2
43.1
21.3
52.5
42.1
Terminal-Bench 2.1 (Claude Code)
47
40.6
18.9
49.2
-
SWE-bench Verified
70.6
69.4
53.2
73.4
52
SWE-bench Pro
47.5
42.9
31.3
49.5
35.7
Card id model:hf:ornith-ai/Ornith-1.5-9B-GGUF · collected 2026-10-02 20:54 UTC · JSON