Ornith 1.5 9B GGUF is the GGUF-format text-generation model card for Ornith-1.5-9B, a 9B dense model in the Ornith-1.5 family. The model card describes Ornith-1.5 as extending Ornith-1.0 through an end-to-end self-improvement approach and lists benchmarks comparing it with Ornith-1.0-9B, Qwen3.5-9B, Qwen3.6-35B-A3B, and Gemma-4-31B. The supplied data also indicates an MIT license and that the base Ornith-1.5-9B model is intended for efficient single-GPU deployment, with a quantized mobile variant noted in the model card.
Format
Q4_K_M GGUF weights
Freshness 80 out of 100. Repository age: 57 days old, Aug 19, 2026. Measures age, not quality.Freshness80/10057 days old
Popularity 88 out of 100. 5,011,351 downloads in 30 days; 540 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.Popularity88/1005M downloads / 30d
Ornith 1.5 35B A3B GGUF is the GGUF-format text-generation model published in the ornith-ai/Ornith-1.5-35B-A3B-GGUF repository under the MIT license. It is the mid-size mixture-of-experts member of the Ornith-1.5 family, activating only about 3B parameters per token. The upstream Ornith-1.5 model extends Ornith-1.0 by jointly optimizing task generation, scaffold construction, and solution rollouts through an end-to-end self-improvement loop with reinforcement learning. The official model card reports benchmark comparisons against Ornith-1.0-35B-A3B, Qwen3.6-35B-A3B, Gemma-4-31B, Muse-Glimmer-30B, and Qwen3.5-397B on coding and agentic evaluations.
Format
Q4_K_M GGUF weights
Freshness 80 out of 100. Repository age: 58 days old, Aug 18, 2026. Measures age, not quality.Freshness80/10058 days old
Popularity 86 out of 100. 3,709,734 downloads in 30 days; 512 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.Popularity86/1003.7M downloads / 30d
Ornith 1.5 35B A3B is a text-generation model from the Ornith-1.5 family, identified as its mid-size mixture-of-experts member. It activates approximately 3B parameters per token. According to the official model card, Ornith-1.5 extends Ornith-1.0 by jointly optimizing task generation, scaffold construction, and solution rollouts within a self-improvement loop. The model card reports that it outperforms similar-sized peer Qwen 3.6-35B across all coding and agentic benchmarks, and outperforms dense models such as Gemma 4-31B and Muse Glimmer-30B by wide margins on agentic coding. The repository is listed under the MIT license and is tagged for text-generation with safetensors.
Model size
35.95B
Format
FP16 weights
Freshness 80 out of 100. Repository age: 58 days old, Aug 18, 2026. Measures age, not quality.Freshness80/10058 days old
Popularity 73 out of 100. 254,974 downloads in 30 days; 729 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.Popularity73/100255K downloads / 30d