GraySoft
Model Comparison

prism-ml/bonsai-8b-ggufvsteichai/qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-gguf

Side-by-side comparison of prism-ml/bonsai-8b-gguf and teichai/qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-gguf: downloads, license, context length, tasks, and benchmarks.

prism-ml/bonsai-8b-gguf

prism-ml · text-generation

End-to-end 1-bit language model for llama.cpp (CUDA, Metal, CPU) > **14.1x** smaller than FP16 | **6.2x** faster on RTX 4090 | **4-5x** lower energy/token

teichai/qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-gguf

TeichAI · text-generation

This model was trained on a **Claude Sonnet 4.5 (reasoning)** dataset with a high reasoning effort. | Model | Effective parameters | Active parameters | | ------------- | ------------- | ------------- | | TeichAI/gpt-oss-20b-claude-4.5-sonnet-high-reasoning-distill-GGUF | 20 B |…

Side-by-side Specifications

prism-ml/bonsai-8b-ggufteichai/qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-gguf
Authorprism-mlTeichAI
Pipeline Tasktext-generationtext-generation
Libraryllama.cpptransformers
Downloads83,30924,326
Likes61824
LicenseUnknownUnknown
Context Length
Created2026-03-182025-11-16
Last Modified2026-04-162025-11-19
Tags
llama.cppgguf1-bitllama-cppcudametalon-deviceprismmlbonsaitext-generation
transformersgguftext-generation-inferenceunslothqwen3_moetext-generationendataset:TeichAI/claude-sonnet-4.5-high-reasoning-250xbase_model:TeichAI/Qwen3-30B-A3B-Thinking-2507-Claude-4.5-Sonnet-High-Reasoning-Distillbase_model:quantized:TeichAI/Qwen3-30B-A3B-Thinking-2507-Claude-4.5-Sonnet-High-Reasoning-Distill

View full details: prism-ml/bonsai-8b-gguf · teichai/qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-gguf