# Ornith-1.5-122B (slim)

> Ornith-1.5-122B is Ornith's open-weight mixture-of-experts reasoning model for coding and agent work, about 125B parameters on Qwen3.5's architecture with a 262,144-token context, published in BF16, FP8, NVFP4, GGUF and MLX and marked MIT.

- Full: https://www.anchorterminal.com/tools/ornith-1-5-122b.md (~10,250 tokens) · this version ~1,980 tokens · JSON https://www.anchorterminal.com/tools/ornith-1-5-122b.json · canonical https://www.anchorterminal.com/tools/ornith-1-5-122b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10 · pricing https://www.anchorterminal.com/tools/ornith-1-5-122b#pricing · reviews https://www.anchorterminal.com/tools/ornith-1-5-122b#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**C · 61/100 · rank #70 of 135 open-weight models · #59 in Open-weight models · not agent-ready · confidence low**


Assessment: The largest Ornith that fits a 128 GB machine, a coding and terminal-agent cousin on Qwen3.5-122B-A10B's architecture with XML tool calls and 262,144 tokens of context. Its 4-bit builds need 84 to 93 GB. The main risk is an absent publisher, with no licence file, safety results or replies, and a card that misstates the hardware.

## Facts

- Kind: Open-weight model · vendor: Ornith · category: Open-weight models · legal entity: not named · provenance 19/100
- Packages: huggingface `ornith-ai/Ornith-1.5-122B`, huggingface `ornith-ai/Ornith-1.5-122B-GGUF`, huggingface `ornith-ai/Ornith-1.5-122B-FP8`, huggingface `ornith-ai/Ornith-1.5-122B-NVFP4`, huggingface `ornith-ai/Ornith-1.5-122B-MLX-4bit`, ollama `ornith-1.5:122b-q4_K_M`
- Auth: None · pricing: Free · x402: no · licence: MIT
- Benchmark probes: not run yet, so Performance is pending
- Surface graded: The open weights at huggingface.co/ornith-ai/Ornith-1.5-122B and Ornith's own GGUF, FP8, NVFP4 and MLX repositories, read from the model card, the files and their metadata, the chat templates, Ornith's blog post and the runtimes' own code on 10 November 2026. Nothing was downloaded or run. Ornith runs no hosted API that we found
- Model: 125,086,497,008 parameters in BF16 per the safetensors metadata, the qwen3_5_moe architecture (Qwen3_5MoeForConditionalGeneration), 48 layers in a 3 to 1 mix of linear and full attention, 256 experts with 8 routed per token, a vision encoder and a multi-token prediction layer. Text and images in, text out. The card calls it a 122B mixture-of-experts model and doesn't state the active parameters
- Files: Sixty-two safetensors shards in BF16 (250.2 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. Ollama's library entry carries an MIT text with the copyright line of deepreinforce.ai. The card says the family builds on Qwen3.5 and Gemma 4, both Apache 2.0, whose notices aren't carried
- 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, and llama.cpp and Ollama commands for the GGUF. Model code for qwen3_5_moe in vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2, the qwen35moe architecture in llama.cpp b12242, an ornith-1.5:122b-q4_K_M entry in Ollama's library and the qwen35moe architecture in LM Studio's catalogue
- Context: 262,144 tokens native (max_position_embeddings in config.json, rope_type default). 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=...>` 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 a single 80 GB GPU, which the BF16 files (250 GB) don't fit. Ornith's GGUF files run from 75.8 GB (Q4_K_M) to 249.4 GB (BF16), its MLX 4-bit build is 69.7 GB, NVFP4 77.7 GB and FP8 133.0 GB. With a fifth added, the 4-bit builds need 84 to 93 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, and doesn't mention the 122B size

- Scores: Capability pending, Reach 75, Risk 50, Agent interface 85, Documentation and upkeep 36 · total over the 7 assessed categories
- Why:  · Reach, Memory 10, since Ornith's own MLX 4-bit build is 69.7 GB and needs about 83.6 GB with the fifth added, over 64 GB and inside the reference m… · Risk, File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code fla… · 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: 27, open questions: 9, both in the full twin
- Capabilities: model.open-weights
- JSON: https://www.anchorterminal.com/api/v1/tools/ornith-1-5-122b.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.
- Support: https://huggingface.co/ornith-ai/Ornith-1.5-122B/discussions; more in the full twin

## Before you call it

1. Start it with `ollama run ornith-1.5:122b-q4_K_M`, or `llama-server -hf ornith-ai/Ornith-1.5-122B-GGUF:Q4_K_M --jinja -c 262144`
2. Budget about 92 GB for the Q4_K_M GGUF with a working context, and less context if the machine has under 100 GB for the model
3. 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
4. Thinking is on by default. Send `chat_template_kwargs` with `enable_thinking` false for short tasks, a switch the card doesn't mention
5. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
6. Use temperature 0.6, top_p 0.95, top_k 20 for coding and temperature 1.0 for general tasks, as the card recommends
7. Add mmproj-Ornith-1.5-122B-BF16.gguf (0.9 GB) for image input in llama.cpp, and validate JSON output yourself, since structured output isn't documented

## Connect

```bash
ollama run ornith-1.5:122b-q4_K_M
# or, with llama.cpp and Ornith's own GGUF:
llama-server -hf ornith-ai/Ornith-1.5-122B-GGUF:Q4_K_M --jinja -c 262144
# or, with the card's vLLM command (abridged):
vllm serve ornith-ai/Ornith-1.5-122B --served-model-name Ornith-1.5-122B --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-1.5:122b-q4_K_M", "messages": [{"role": "user", "content": "Hello!"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Qwen3-Embedding-8B | BB | 75.4 | 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 | 73.6 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-4b.min.md |
| Gemma 4 12B IT | BB | 72.3 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-12b-it.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 |


## Panel reviews (0, desk reviews from public material, no calls made)