Model Comparison

ggml-org/gemma-4-31b-it-ggufvsmradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf

Side-by-side comparison of ggml-org/gemma-4-31b-it-gguf and mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf: downloads, license, context length, tasks, and benchmarks.

ggml-org/gemma-4-31b-it-gguf

ggml-org · —

# gemma-4-31B-it-GGUF Recommended way to run this model: ``sh llama-server -hf ggml-org/gemma-4-31B-it-GGUF `` Then, access http://localhost:8080

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

Side-by-side Specifications

	ggml-org/gemma-4-31b-it-gguf	mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf
Author	ggml-org	mradermacher
Pipeline Task	—	—
Library	—	transformers
Downloads	52,521	22,565
Likes	34	0
License	Unknown	Unknown
Context Length	—	—
Created	2026-04-01	2026-03-25
Last Modified	2026-04-12	2026-03-30
Tags	ggufbase_model:google/gemma-4-31B-itbase_model:quantized:google/gemma-4-31B-itendpoints_compatibleregion:usconversational	transformersggufenbase_model:vpyn/MiniMax-M2.5-CARVE-v1-BF16base_model:quantized:vpyn/MiniMax-M2.5-CARVE-v1-BF16endpoints_compatibleregion:usimatrixconversational

View full details: ggml-org/gemma-4-31b-it-gguf · mradermacher/minimax-m2.5-carve-v1-bf16-i1-gguf