Qwen-3.8-27B, Nemotron-3.5-Lightning-30B-A3B, Ornith-1.5-35B-A3B, Muse-Glimmer-30B oQ8e comparison
Summary
A comparison of multiple AI models including Qwen, Nemotron, Ornith, and Muse-Glimmer on benchmarks, with Ornith performing well and TielCoder showing potential in coding tasks.
Similar Articles
Local benchmarks with a RTX 3090 - Qwen3.6 27b vs Ornith
User runs local benchmarks comparing Qwen3.6 27b, Gemma4 26B, and Ornith1.0 35B on an RTX 3090 using inspect-ai. Results show Qwen leading in knowledge and coding, while Ornith is competitive in grounding and recall.
35B-A3B tool calling benchmark: Original Qwen vs. KAT Coder, Ornith and Tiel-Coder
The article benchmarks fine-tuned Qwen3.6-35B-A3B models for tool calling capabilities, showing Ornith 1.5 and Tiel-Coder perform best, approaching scores of larger Qwen models. The study uses extensive GPU time and the tool-eval-bench utility for evaluation.
ornith-ai/Ornith-1.5-35B-A3B
Ornith-1.5-35B-A3B is a mixture-of-experts AI model that activates only 3B parameters per token and outperforms similar-sized models like Qwen and Gemma in coding and agentic benchmarks.
@TheAhmadOsman: Will Qwen 3.8 27B make a comeback against Muse Glimmer 30B? In all cases, extremely happy about this release
A user expresses excitement about a new AI model release and speculates whether Qwen 3.8 27B can compete with Muse Glimmer 30B.
I made a web-design benchmark for local models (Muse Glimmer 30B vs Qwen 3.6 27b vs Deepseek V4 Flash 0731)
The author created a web-design benchmark for local AI models and compared Muse Glimmer 30B, Qwen 3.6 27b, and Deepseek V4 Flash 0731.