GraySoft
Download guIDE →
Model Comparison

m4-ai/tinymistral-248m-v2-instruct-ggufvsmradermacher/total04-deepseek-r1-distill-llama-70b-heretic-i1-gguf

Side-by-side comparison of m4-ai/tinymistral-248m-v2-instruct-gguf and mradermacher/total04-deepseek-r1-distill-llama-70b-heretic-i1-gguf: downloads, license, context length, tasks, and benchmarks.

m4-ai/tinymistral-248m-v2-instruct-gguf

M4-ai · —

GGUF version of Locutusque/TinyMistral-248M-v2-Instruct. # Recommended inference parameters `` do_sample: true temperature: 0.1 top_p: 0.14 top_k: 12 repetition_penalty: 1.1 ` # Recommended prompt template ` user\n{user message}\nassistant\n{assistant message} ``

mradermacher/total04-deepseek-r1-distill-llama-70b-heretic-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/CCSSNE/Total04-DeepSeek-R1-Distill-Llama-70B-heretic ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Total04-Deep…

Side-by-side Specifications

m4-ai/tinymistral-248m-v2-instruct-ggufmradermacher/total04-deepseek-r1-distill-llama-70b-heretic-i1-gguf
AuthorM4-aimradermacher
Pipeline Task——
Library—transformers
Downloads29,48221,302
Likes60
LicenseUnknownUnknown
Context Length——
Created2024-02-032026-04-02
Last Modified2024-02-032026-04-03
Tags
ggufendataset:HuggingFaceH4/ultrachat_200kbase_model:Locutusque/TinyMistral-248M-v2-Instructbase_model:quantized:Locutusque/TinyMistral-248M-v2-Instructlicense:apache-2.0endpoints_compatibleregion:us
transformersggufhereticuncensoreddecensoredabliteratedenbase_model:CCSSNE/Total04-DeepSeek-R1-Distill-Llama-70B-hereticbase_model:quantized:CCSSNE/Total04-DeepSeek-R1-Distill-Llama-70B-hereticlicense:mit

View full details: m4-ai/tinymistral-248m-v2-instruct-gguf · mradermacher/total04-deepseek-r1-distill-llama-70b-heretic-i1-gguf