GraySoft
Download guIDE →
Model Comparison

mradermacher/minimax-m2.5-carve-v1-bf16-i1-ggufvsprism-ml/bonsai-8b-gguf

Side-by-side comparison of mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf and prism-ml/bonsai-8b-gguf: downloads, license, context length, tasks, and benchmarks.

mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/vpyn/MiniMax-M2.5-CARVE-v1-BF16 ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/MiniMax-M2.5-CARVE-v1-BF16-GGUF

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

Side-by-side Specifications

mradermacher/minimax-m2.5-carve-v1-bf16-i1-ggufprism-ml/bonsai-8b-gguf
Authormradermacherprism-ml
Pipeline Task—text-generation
Librarytransformersllama.cpp
Downloads22,56583,309
Likes0618
LicenseUnknownUnknown
Context Length——
Created2026-03-252026-03-18
Last Modified2026-03-302026-04-16
Tags
transformersggufenbase_model:vpyn/MiniMax-M2.5-CARVE-v1-BF16base_model:quantized:vpyn/MiniMax-M2.5-CARVE-v1-BF16endpoints_compatibleregion:usimatrixconversational
llama.cppgguf1-bitllama-cppcudametalon-deviceprismmlbonsaitext-generation

View full details: mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf · prism-ml/bonsai-8b-gguf