Ornith 1.5 35B A3B GGUF
The Ornith 1.5 35B A3B GGUF is a text-generation model from the ornith-ai/Ornith-1.5-35B-A3B-GGUF repository, licensed under MIT, with GGUF tagging for local inference. Its official model card describes Ornith-1.5-35B-A3B as a mid-size mixture-of-experts member of the Ornith-1.5 family that activates roughly 3B parameters per token. The model is presented as a step toward foundation models through end-to-end self-improvement, extending Ornith-1.0 by jointly optimizing task generation, scaffold construction, and solution rollouts through reinforcement learning. The card states it outperforms similarly sized peers on coding and agentic benchmarks, though specific numerical claims should be independently verified.
At a glance
- Architecture
- unknown
- License
- mit
- Software
- Ollama, llama.cpp
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Local text generation with GGUF-formatted models
- Coding assistance tasks
- Agentic workflows and tool-use scenarios
- Instruction-following conversational generation
- Experimentation with mixture-of-experts inference
Tradeoffs
- No explicit hardware requirements, memory needs, or compatibility details are provided in the supplied facts
- No information about supported quantization levels beyond GGUF is included
- Performance claims are drawn from the model card and are not independently verified
- The activation size does not imply low total memory needs at runtime
- No details are given about context length limits, language support, or safety considerations
Ways to run it
Ollama · Windows, macOS, Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
ollama run hf.co/ornith-ai/Ornith-1.5-35B-A3B-GGUFllama.cpp · Windows, macOS, Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
llama-server -hf ornith-ai/Ornith-1.5-35B-A3B-GGUF --port 8000 -c 262144Explore its uses
Keep exploring
Bonsai 2 · 27B
A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.
DeepSeek V4.1 Flash
A multimodal reasoning model with a compressed key-value cache, published as open weights.
Qwen3.8-Flash-Next
An experimental open-weight multimodal model with sparse attention and 262K native context.