Model Intelligence Sheet
FForty7/gpt-oss-20b-claude-4.5-sonnet-high-reasoning-distill-GGUF overview
Important This model is still in developement. For the most reliable performance use the following sampling parameters: temperature : 0.1 0.2 top k : 100 min p…
Runs locally from ~12.85 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gpt-oss-20b-claude-4.5-sonnet-high-reasoning-distill-bf16.gguf | GGUF | BF16 | 12.85 GB | Download |
Model Details
Model README
---
base_model: unsloth/gpt-oss-20b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gpt_oss
license: apache-2.0
language:
- en
datasets:
- Liontix/claude-sonnet-4.5-high-reasoning-250x
---
Important
This model is still in developement.
For the most reliable performance use the following sampling parameters:
temperature: 0.1-0.2top_k: 100min_p: 0.00top_p: 1.00repeat_penalty: 1.0 (off)
Check back later for updates.
Uploaded finetuned model
- Developed by: armand0e
- License: apache-2.0
- Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit
This gpt_oss model was trained 2x faster with Unsloth and Huggingface's TRL library.
Run FForty7/gpt-oss-20b-claude-4.5-sonnet-high-reasoning-distill-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models