Edit model card

aya-23-35B-IMat-GGUF

Llama.cpp imatrix quantization of CohereForAI/aya-23-35B

Original Model: CohereForAI/aya-23-35B
Original dtype: FP16 (float16)
Quantized by: llama.cpp b2998
IMatrix dataset: here

Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
aya-23-35B.Q8_0/* Q8_0 37.18GB βœ… Available βšͺ No βœ‚ Yes
aya-23-35B.Q6_K.gguf Q6_K 28.71GB βœ… Available βšͺ No πŸ“¦ No
aya-23-35B.Q4_K.gguf Q4_K 21.53GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.Q3_K.gguf Q3_K 17.62GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.Q2_K.gguf Q2_K 13.82GB βœ… Available 🟒 Yes πŸ“¦ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
aya-23-35B.FP16/* F16 69.97GB βœ… Available βšͺ No βœ‚ Yes
aya-23-35B.Q5_K.gguf Q5_K 25.01GB βœ… Available βšͺ No πŸ“¦ No
aya-23-35B.Q5_K_S.gguf Q5_K_S 24.34GB βœ… Available βšͺ No πŸ“¦ No
aya-23-35B.Q4_K_S.gguf Q4_K_S 20.38GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.Q3_K_L.gguf Q3_K_L 19.15GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.Q3_K_S.gguf Q3_K_S 15.86GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.Q2_K_S.gguf Q2_K_S 12.74GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ4_NL.gguf IQ4_NL 20.23GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ4_XS.gguf IQ4_XS 19.20GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ3_M.gguf IQ3_M 16.70GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ3_S.gguf IQ3_S 15.86GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ3_XS.gguf IQ3_XS 15.09GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ3_XXS.gguf IQ3_XXS 13.83GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ2_M.gguf IQ2_M 12.68GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ2_S.gguf IQ2_S 11.84GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ2_XS.gguf IQ2_XS 11.10GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ2_XXS.gguf IQ2_XXS 10.19GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ1_M.gguf IQ1_M 9.15GB βœ… Available 🟒 Yes πŸ“¦ No
aya-23-35B.IQ1_S.gguf IQ1_S 8.52GB βœ… Available 🟒 Yes πŸ“¦ No

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download legraphista/aya-23-35B-IMat-GGUF --include "aya-23-35B.Q8_0.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/aya-23-35B-IMat-GGUF --include "aya-23-35B.Q8_0/*" --local-dir aya-23-35B.Q8_0
# see FAQ for merging GGUF's

FAQ

Why is the IMatrix not applied everywhere?

According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

How do I merge a split GGUF?

  1. Make sure you have gguf-split available
  2. Locate your GGUF chunks folder (ex: aya-23-35B.Q8_0)
  3. Run gguf-split --merge aya-23-35B.Q8_0/aya-23-35B.Q8_0-00001-of-XXXXX.gguf aya-23-35B.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!

Downloads last month
692
GGUF
Model size
35B params
Architecture
command-r

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for legraphista/aya-23-35B-IMat-GGUF

Quantized
(10)
this model

Collection including legraphista/aya-23-35B-IMat-GGUF