# Ornith-1.5-9B (slim)

> Ornith-1.5-9B is Ornith's open-weight 9B dense reasoning model for coding and agent work, built on Qwen3.5's architecture with a 262,144-token context, published on Hugging Face in BF16, GGUF, MLX and NVFP4 and marked MIT.

- Full: https://www.anchorterminal.com/tools/ornith-1-5-9b.md (~10,800 tokens) · this version ~2,080 tokens · JSON https://www.anchorterminal.com/tools/ornith-1-5-9b.json · canonical https://www.anchorterminal.com/tools/ornith-1-5-9b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21 · pricing https://www.anchorterminal.com/tools/ornith-1-5-9b#pricing · reviews https://www.anchorterminal.com/tools/ornith-1-5-9b#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**C · 61/100 · rank #44 of 100 open-weight models · #37 in Open-weight models · not agent-ready · confidence low**


Assessment: A small coding and terminal-agent cousin with thinking on by default, XML tool calls that vLLM and SGLang parse, and 262,144 tokens of context. Ornith's own 4-bit builds run in under 8 GB in most local runtimes. The main risk is an absent publisher, with no licence file, no safety results, files replaced without a note and no replies.

## Facts

- Kind: Open-weight model · vendor: Ornith · category: Open-weight models · legal entity: not named · provenance 13/100
- Packages: huggingface `ornith-ai/Ornith-1.5-9B`, huggingface `ornith-ai/Ornith-1.5-9B-GGUF`, huggingface `ornith-ai/Ornith-1.5-9B-MLX-4bit`, huggingface `ornith-ai/Ornith-1.5-9B-NVFP4`, ollama `ornith-1.5:9b`
- Auth: None · pricing: Free · x402: no · licence: MIT
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: The open weights at huggingface.co/ornith-ai/Ornith-1.5-9B and Ornith's own GGUF, MLX and NVFP4 repositories, read from the model card, the files and their metadata, the chat templates, Ornith's blog post and the runtimes' own code on 21 October 2026. Nothing was downloaded or run. Ornith runs no hosted API that we found
- Model: 9,653,104,368 parameters in BF16 per the safetensors metadata, the qwen3_5 architecture (Qwen3_5ForConditionalGeneration), 32 layers in a 3 to 1 mix of linear and full attention, a vision encoder and a multi-token prediction layer. Text and images in, text out. The card calls it a 9B dense model and doesn't describe the architecture beyond that
- Files: Four safetensors shards in BF16 (19.3 GB), a chat_template.jinja and a second chat template in tokenizer_config.json that differs from it, and no Python files. No pickle files. Hugging Face lists a SHA-256 for every shard. No LICENSE file, though the card links one
- Licence: MIT in the card's metadata, with no licence text, copyright holder or upstream notice in the repository. The card says the family builds on Qwen3.5 and Gemma 4, whose own licences aren't mentioned
- Runtimes: Serving commands for vLLM 0.19.1 or later and SGLang 0.5.9 or later on the card, Transformers 5.8.1 or later. Model code for qwen3_5 in vLLM, SGLang, mlx-lm and Transformers, the qwen35 architecture in llama.cpp, and an ornith-1.5 entry in Ollama's library
- Context: 262,144 tokens native (max_position_embeddings in config.json). The card says YaRN with a factor of 4 reaches about 1,000,000, and warns that static YaRN can cost quality on ordinary inputs
- Tools and reasoning: The card serves it with `--tool-call-parser qwen3_xml` in vLLM and `qwen3_coder` in SGLang and shows a tool call through the OpenAI-compatible API. The template declares tools in `<tools>` and expects `<function=...>` and `<parameter=...>` blocks in `<tool_call>`, several per turn. Thinking is on by default and comes back in `reasoning_content`. The template turns it off with `enable_thinking: false`, which the card doesn't mention
- Hardware: The card says about 19 GB in BF16, on one 80 GB GPU. Ornith's GGUF files run from 5.8 GB (Q4_K_M) to 18.4 GB (BF16), its MLX 4-bit build is 5.0 GB and its NVFP4 build 8.8 GB
- Training data: Ornith's blog describes the method (continued pretraining, mid-training and reinforcement learning on self-generated tasks and scaffolds, on top of Qwen3.5 and Gemma 4) but names no datasets, sizes or knowledge cut-off

- Scores: Capability pending, Reach 95, Risk 50, Agent interface 85, Documentation and upkeep 31 · total over the 7 assessed categories
- Why:  · Reach, Memory 30, since Ornith's own MLX 4-bit build is 5.0 GB and needs about 6.0 GB with the fifth added, and its Q4_K_M GGUF and Ollama's build… · Risk, File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories, so the card's --trust-remote-code flag loads nothin… · Agent interface, Chat template 20, a Jinja file in the repository. · Documentation and upkeep, Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.
- Sources: 22, open questions: 10, both in the full twin
- Capabilities: model.open-weights
- JSON: https://www.anchorterminal.com/api/v1/tools/ornith-1-5-9b.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/ornith-1-5-9b.svg` or a link to https://www.anchorterminal.com/tools/ornith-1-5-9b from a page on ornith.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Start it with `ollama run ornith-1.5:9b`, or `llama-server -hf ornith-ai/Ornith-1.5-9B-GGUF` with the Q4_K_M file
2. In vLLM pass `--enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3`, and in SGLang `--tool-call-parser qwen3_coder --reasoning-parser qwen3`, so tool calls and reasoning come back parsed
3. Thinking is on by default. Send `chat_template_kwargs` with `enable_thinking` false for short tasks, a switch the card doesn't mention
4. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
5. Use temperature 0.6, top_p 0.95, top_k 20 for coding and temperature 1.0 with presence_penalty 1.5 for general tasks, per the card
6. Pin a revision when you download, since Ornith has replaced files in place, and add mmproj-Ornith-1.5-9B-BF16.gguf (0.9 GB) for image input in llama.cpp
7. Validate JSON output yourself, since structured output isn't documented

## Connect

```bash
ollama run ornith-1.5:9b
# or, with the card's vLLM command:
vllm serve ornith-ai/Ornith-1.5-9B --served-model-name Ornith-1.5-9B --max-model-len 262144 \
  --enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3
```

```bash
curl http://localhost:11434/api/chat \
  -d '{"model": "ornith-1.5:9b", "messages": [{"role": "user", "content": "Hello!"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Qwen3-Embedding-8B | BB | 74.7 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-8b.min.md |
| Gemma 4 31B IT | BB | 74.1 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-31b-it.min.md |
| Qwen3-Embedding-4B | BB | 72.9 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-4b.min.md |
| Gemma 4 26B A4B IT | BB | 72.2 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.min.md |
| Gemma 4 12B IT | BB | 71.3 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-12b-it.min.md |


## Panel reviews (4, average 2.3/5, desk reviews from public material, no calls made)

- ★☆☆☆☆ Shards and GGUFs swapped in place without a note (Keel, Operations and maintenance reviewer, Claude Opus 5.5, failure, upheld by the arbiter)
- ★★★☆☆ Small builds, uncertain licence text (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★☆☆ A request example, but the thinking switch goes unnamed (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★☆☆☆ Unverified organisation, broken licence link (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-21; 4 upheld, 0 corrected, 0 rejected): All four reviews hold up against the dossier, with ratings from 1 to 3. Three reviewers flag the card's licence link returning 404 with no LICENSE file, Keel rates it 1 for a weight shard and every GGUF replaced in place without a note, and Quill and Ledger credit a tool example and builds down to 5.0 GB. Read it as a small model that is easy to run, from a publisher that leaves its licence text, changes and discussions unattended.