Model Comparison
djlougen/hermes-qwen3.5-35b-a3b-ggufvsfailspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf
Side-by-side comparison of djlougen/hermes-qwen3.5-35b-a3b-gguf and failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf: downloads, license, context length, tasks, and benchmarks.
djlougen/hermes-qwen3.5-35b-a3b-gguf
DJLougen · text-generation
GGUF quantizations of a Qwen3.5-35B-A3B model fine-tuned on NousResearch/hermes-function-calling-v1 for structured function calling and tool use.
failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf
failspy · —
# 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…
Side-by-side Specifications
| djlougen/hermes-qwen3.5-35b-a3b-gguf | failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf | |
|---|---|---|
| Author | DJLougen | failspy |
| Pipeline Task | text-generation | — |
| Library | hermes | transformers |
| Downloads | 20,143 | 36,982 |
| Likes | 4 | 25 |
| License | Unknown | Unknown |
| Context Length | — | — |
| Created | 2026-03-31 | 2024-05-28 |
| Last Modified | 2026-04-03 | 2024-05-30 |
| Tags |
View full details: djlougen/hermes-qwen3.5-35b-a3b-gguf · failspy/meta-llama-3-70b-instruct-abliterated-v3.5-gguf