GraySoft
Model Comparison

mradermacher/llama3.3-8b-instruct-thinking-heretic-uncensored-claude-4.5-opus-high-reasoning-i1-ggufvssugoitoolkit/sugoi-14b-ultra-gguf

Side-by-side comparison of mradermacher/llama3.3-8b-instruct-thinking-heretic-uncensored-claude-4.5-opus-high-reasoning-i1-gguf and sugoitoolkit/sugoi-14b-ultra-gguf: downloads, license, context length, tasks, and benchmarks.

mradermacher/llama3.3-8b-instruct-thinking-heretic-uncensored-claude-4.5-opus-high-reasoning-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/DavidAU/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggi…

sugoitoolkit/sugoi-14b-ultra-gguf

sugoitoolkit · translation

Unleashing the full potential of the previous sugoi 14B model, **Sugoi 14B Ultra** delivers near-double translation accuracy compared to its quantized predecessor—achieving a BLEU score of **21.38 vs 13.67**. Its prompt-following skills rival those of Qwen 2.5 Base, especially w…

Side-by-side Specifications

mradermacher/llama3.3-8b-instruct-thinking-heretic-uncensored-claude-4.5-opus-high-reasoning-i1-ggufsugoitoolkit/sugoi-14b-ultra-gguf
Authormradermachersugoitoolkit
Pipeline Tasktranslation
Librarytransformers
Downloads101,521149,473
Likes438
LicenseUnknownUnknown
Context Length
Created2026-01-022025-08-19
Last Modified2026-01-022025-08-26
Tags
transformersggufthinkingreasoninginstructhereticuncensoredabliteratedClaude4.5-Opuscreative
gguftranslationjaenbase_model:sugoitoolkit/Sugoi-14B-Ultra-HFbase_model:quantized:sugoitoolkit/Sugoi-14B-Ultra-HFlicense:apache-2.0endpoints_compatibleregion:usconversational

View full details: mradermacher/llama3.3-8b-instruct-thinking-heretic-uncensored-claude-4.5-opus-high-reasoning-i1-gguf · sugoitoolkit/sugoi-14b-ultra-gguf