Gemma 2
Collection
6 items
•
Updated
Llama.cpp imatrix quantization of google/gemma-2-9b-it
Original Model: google/gemma-2-9b-it
Original dtype: BF16
(bfloat16
)
Quantized by: llama.cpp b3266
IMatrix dataset: here
Status: ✅ Available
Link: here
Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
---|---|---|---|---|---|
gemma-2-9b-it.Q8_0.gguf | Q8_0 | 9.83GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.Q6_K.gguf | Q6_K | 7.59GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.Q4_K.gguf | Q4_K | 5.76GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q3_K.gguf | Q3_K | 4.76GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q2_K.gguf | Q2_K | 3.81GB | ✅ Available | 🟢 IMatrix | 📦 No |
Filename | Quant type | File Size | Status | Uses IMatrix | Is Split |
---|---|---|---|---|---|
gemma-2-9b-it.BF16.gguf | BF16 | 18.49GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.FP16.gguf | F16 | 18.49GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.Q8_0.gguf | Q8_0 | 9.83GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.Q6_K.gguf | Q6_K | 7.59GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.Q5_K.gguf | Q5_K | 6.65GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.Q5_K_S.gguf | Q5_K_S | 6.48GB | ✅ Available | ⚪ Static | 📦 No |
gemma-2-9b-it.Q4_K.gguf | Q4_K | 5.76GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q4_K_S.gguf | Q4_K_S | 5.48GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ4_NL.gguf | IQ4_NL | 5.44GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ4_XS.gguf | IQ4_XS | 5.18GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q3_K.gguf | Q3_K | 4.76GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q3_K_L.gguf | Q3_K_L | 5.13GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q3_K_S.gguf | Q3_K_S | 4.34GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ3_M.gguf | IQ3_M | 4.49GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ3_S.gguf | IQ3_S | 4.34GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ3_XS.gguf | IQ3_XS | 4.14GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ3_XXS.gguf | IQ3_XXS | 3.80GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q2_K.gguf | Q2_K | 3.81GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.Q2_K_S.gguf | Q2_K_S | 3.55GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ2_M.gguf | IQ2_M | 3.43GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ2_S.gguf | IQ2_S | 3.21GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ2_XS.gguf | IQ2_XS | 3.07GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ2_XXS.gguf | IQ2_XXS | 2.82GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ1_M.gguf | IQ1_M | 2.55GB | ✅ Available | 🟢 IMatrix | 📦 No |
gemma-2-9b-it.IQ1_S.gguf | IQ1_S | 2.38GB | ✅ Available | 🟢 IMatrix | 📦 No |
If you do not have hugginface-cli installed:
pip install -U "huggingface_hub[cli]"
Download the specific file you want:
huggingface-cli download legraphista/gemma-2-9b-it-IMat-GGUF --include "gemma-2-9b-it.Q8_0.gguf" --local-dir ./
If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:
huggingface-cli download legraphista/gemma-2-9b-it-IMat-GGUF --include "gemma-2-9b-it.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's
<bos><start_of_turn>user
{user_prompt}<end_of_turn>
<start_of_turn>model
{assistant_response}<end_of_turn>
<start_of_turn>user
{next_user_prompt}<end_of_turn>
llama.cpp/main -m gemma-2-9b-it.Q8_0.gguf --color -i -p "prompt here (according to the chat template)"
According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).
gguf-split
availablegguf-split
, navigate to https://github.com/ggerganov/llama.cpp/releasesgguf-split
gemma-2-9b-it.Q8_0
)gguf-split --merge gemma-2-9b-it.Q8_0/gemma-2-9b-it.Q8_0-00001-of-XXXXX.gguf gemma-2-9b-it.Q8_0.gguf
gguf-split
to the first chunk of the split.Got a suggestion? Ping me @legraphista!
Base model
google/gemma-2-9b-it