failspy/meta-llama-3-70b-instruct-abliterated-v3.5-ggufvsunsloth/mistral-large-3-675b-instruct-2512-gguf
Side-by-side comparison of failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf and unsloth/mistral-large-3-675b-instruct-2512-gguf: downloads, license, context length, tasks, and benchmarks.
failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf
# Llama-3-70B-Instruct-abliterated-v3.5 Model Card My original Jupyter "cookbook" to replicate the methodology can be found here My personal library o' code used (WIP, looking to improve and generalize) This is meta-llama/Meta-Llama-3-70B-Instruct with orthogonalized bfloat16 sa…
unsloth/mistral-large-3-675b-instruct-2512-gguf
From our family of large models, **Mistral Large 3** is a state-of-the-art general-purpose **Multimodal granular Mixture-of-Experts** model with **41B active parameters** and **675B total parameters** trained from the ground up. This model is the instruct post-trained version, f…
Side-by-side Specifications
| failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf | unsloth/mistral-large-3-675b-instruct-2512-gguf | |
|---|---|---|
| Author | failspy | unsloth |
| Pipeline Task | — | — |
| Library | transformers | — |
| Downloads | 36,982 | 30,621 |
| Likes | 25 | 17 |
| License | Unknown | Unknown |
| Context Length | — | — |
| Created | 2024-05-28 | 2025-12-07 |
| Last Modified | 2024-05-30 | 2025-12-16 |
| Tags |
View full details: failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf · unsloth/mistral-large-3-675b-instruct-2512-gguf