GGUF models by 893790183LZW
34 GGUF models quantized by 893790183LZW on Hugging Face. Sizes run from 163M to 8.03B parameters. The longest trained context is 128K tokens.
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · 893790183LZW
Params7.62B
Context128K
Smallest3.8 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · 893790183LZW
Params7.62B
Context128K
Smallest6.3 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · 893790183LZW
Params7.62B
Context128K
Q4_K_M4.7 GB
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · 893790183LZW
Params8.03B
Context128K
Q4_K_M4.9 GB