Ornith 1.5 9B GGUF
Ornith 1.5 9B GGUF is a GGUF-packaged text-generation model from ornith-ai/Ornith-1.5-9B-GGUF under the MIT license. It is the 9B dense member of the Ornith-1.5 family; the model card describes it as designed for efficient single-GPU deployment and an edge-deployable mobile variant. The source material also describes Ornith-1.5 as building on Ornith-1.0 with an expanded self-improvement loop and reports benchmark results.
At a glance
- Architecture
- unknown
- License
- mit
- Software
- 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 a GGUF-formatted model
- Running a 9B dense model for single-GPU deployment, as described in the model card
- Exploring coding-related benchmark tasks such as Terminal-Bench 2.1, as reported in the model card results
- Research or experimentation with the Ornith-1.5 self-improvement approach described in the source
- Text-generation workflows where the MIT license and GGUF packaging are relevant
Tradeoffs
- The supplied source data is truncated and does not include the full official model card
- No numerical hardware requirements such as GPU memory, RAM, or disk space are provided
- No compatibility information for specific runtimes, frameworks, or quantization formats is provided
- No testing, validation, or performance claims were performed or verified from this summary
- Missing facts such as exact deployment constraints, supported languages, and full benchmark results should not be inferred
Ways to run it
llama.cpp · Windows, macOS, Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
llama-server -hf hf.co/ornith-ai/Ornith-1.5-9B-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.