GraySoft
Model Comparison

prism-ml/bonsai-8b-ggufvsteichai/glm-4.7-flash-claude-opus-4.5-high-reasoning-distill-gguf

Side-by-side comparison of prism-ml/bonsai-8b-gguf and teichai/glm-4.7-flash-claude-opus-4.5-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/glm-4.7-flash-claude-opus-4.5-high-reasoning-distill-gguf

TeichAI · —

This model was trained on a small reasoning dataset of **Claude Opus 4.5**, with reasoning effort set to High. ---

Side-by-side Specifications

prism-ml/bonsai-8b-ggufteichai/glm-4.7-flash-claude-opus-4.5-high-reasoning-distill-gguf
Authorprism-mlTeichAI
Pipeline Tasktext-generation
Libraryllama.cpp
Downloads83,30926,293
Likes618497
LicenseUnknownUnknown
Context Length
Created2026-03-182026-01-22
Last Modified2026-04-162026-02-22
Tags
llama.cppgguf1-bitllama-cppcudametalon-deviceprismmlbonsaitext-generation
gguftext-generation-inferencellama.cppunslothglm4_moe_litedataset:TeichAI/claude-4.5-opus-high-reasoning-250xbase_model:TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distillbase_model:quantized:TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distilllicense:apache-2.0endpoints_compatible

View full details: prism-ml/bonsai-8b-gguf · teichai/glm-4.7-flash-claude-opus-4.5-high-reasoning-distill-gguf