Edit model card

Llamacpp Quantizations of c4ai-command-r-v01

Using llama.cpp release b2440 for quantization.

Original model: https://huggingface.co/CohereForAI/c4ai-command-r-v01

Download a file (not the whole branch) from below:

Filename Quant type File Size Description
c4ai-command-r-v01-Q8_0.gguf Q8_0 37.17GB Extremely high quality, generally unneeded but max available quant.
c4ai-command-r-v01-Q6_K.gguf Q6_K 28.70GB Very high quality, near perfect, recommended.
c4ai-command-r-v01-Q5_K_M.gguf Q5_K_M 25.00GB High quality, very usable.
c4ai-command-r-v01-Q5_K_S.gguf Q5_K_S 24.33GB High quality, very usable.
c4ai-command-r-v01-Q5_0.gguf Q5_0 24.33GB High quality, older format, generally not recommended.
c4ai-command-r-v01-Q4_K_M.gguf Q4_K_M 21.52GB Good quality, similar to 4.25 bpw.
c4ai-command-r-v01-Q4_K_S.gguf Q4_K_S 20.37GB Slightly lower quality with small space savings.
c4ai-command-r-v01-Q4_0.gguf Q4_0 20.22GB Decent quality, older format, generally not recommended.
c4ai-command-r-v01-Q3_K_L.gguf Q3_K_L 19.14GB Lower quality but usable, good for low RAM availability.
c4ai-command-r-v01-Q3_K_M.gguf Q3_K_M 17.61GB Even lower quality.
c4ai-command-r-v01-Q3_K_S.gguf Q3_K_S 15.86GB Low quality, not recommended.
c4ai-command-r-v01-Q2_K.gguf Q2_K 13.81GB Extremely low quality, not recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month
1,750
GGUF
Model size
35B params
Architecture
command-r