Brianpuz/DeepSeek-R1-DRAFT-Qwen2.5-0.5B-Q4_K_M-GGUF
Absolutely tremendous! This repo features GGUF quantized versions of alamios/DeepSeek-R1-DRAFT-Qwen2.5-0.5B — made possible using the very powerful llama.cpp. Believe me, it's fast, it's smart, it's winning.
Quantized Versions:
Only the best quantization. You’ll love it.
Run with llama.cpp
Just plug it in, hit the command line, and boom — you're running world-class AI, folks:
llama-cli --hf-repo Brianpuz/DeepSeek-R1-DRAFT-Qwen2.5-0.5B-Q4_K_M-GGUF --hf-file deepseek-r1-draft-qwen2.5-0.5b-q4_k_m.gguf -p "AI First, but also..."
This beautiful Hugging Face Space was brought to you by the amazing team at Antigma Labs. Great people. Big vision. Doing things that matter — and doing them right. Total winners.
- Downloads last month
- 50
Hardware compatibility
Log In
to view the estimation
4-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Brianpuz/DeepSeek-R1-DRAFT-Qwen2.5-0.5B-Q4_K_M-GGUF
Base model
Qwen/Qwen2.5-0.5B
Finetuned
alamios/DeepSeek-R1-DRAFT-Qwen2.5-0.5B