Downloads · 30 days
40
9% of all-time downloads
gpt-oss-20b-gguf
Lutifya/gpt-oss-20b-gguf
gpt-oss-20b-gguf is a machine learning model from Lutifya. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Versioni quantizzate del modello GPT-OSS-20B di OpenAI in formato GGUF per llama.cpp.
All-time downloads
466
Public
Repo size
53.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf53.9 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Aug 21, 2025
- Updated
- Aug 21, 2025
- SHA
- 6dd762e8
Base models
Model card
From the Hugging Face model README
GPT-OSS-20B GGUF
Versioni quantizzate del modello GPT-OSS-20B di OpenAI in formato GGUF per llama.cpp.
📊 Versioni disponibili
| Formato | Dimensione | Qualità | VRAM | Utilizzo |
|---|---|---|---|---|
| f16 | ~39GB | Massima | 40GB+ | Server/A100 |
| q2_k | ~11GB | Ultra-compatta | 12GB | CPU/RTX 4060 |
Altre quantizzazioni (q8_0, q4_k_m, q4_k_s) saranno aggiunte successivamente.
🚀 Come usare
# Download repository completo
git clone https://huggingface.co/Lutifya/gpt-oss-20b-gguf
# Download file singolo
wget https://huggingface.co/Lutifya/gpt-oss-20b-gguf/resolve/main/gpt-oss-20b-f16.gguf
wget https://huggingface.co/Lutifya/gpt-oss-20b-gguf/resolve/main/gpt-oss-20b-q2_k.gguf
⚡ llama.cpp
# Massima qualità (f16)
./llama-cli -m gpt-oss-20b-f16.gguf -p "Your prompt here"
# Ultra-compatto (q2_k)
./llama-cli -m gpt-oss-20b-q2_k.gguf -p "Your prompt here"
# Server
./llama-server -m gpt-oss-20b-f16.gguf --host 0.0.0.0 --port 8080
📝 Note
- Modello base: openai/gpt-oss-20b
- Fine-tuning: LoRA applicato e merged
- Conversione: llama.cpp 2025-08-21
- Hardware consigliato: GPU NVIDIA con CUDA
🏷️ License
Stesso del modello originale OpenAI GPT-OSS-20B.
- License
- mit
- Languages
- en
- Created
- Aug 21, 2025
- Updated
- Aug 21, 2025