Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,7 @@ Here are some benchmar results:
|
|
| 20 |
| [This model (older version)](https://huggingface.co/stduhpf/google-gemma-3-4b-it-qat-q4_0-gguf-small/blob/359d9494e5e9276e5c4aec2a9e0bdebd74310b1a/gemma-3-4b-it-q4_0_s.gguf) | 2.36 GB | 14.5943 +/- 0.13405 | 65.675% |
|
| 21 |
| [Q4_0 (bartowski)](https://huggingface.co/bartowski/google_gemma-3-1b-it-GGUF/blob/main/google_gemma-3-4b-it-Q4_0.gguf) | 2.37 GB | 16.8002 +/- 0.16519 | 65.65% |
|
| 22 |
| [QAT Q4_0 (google)](https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-gguf/blob/main/gemma-3-4b-it-q4_0.gguf) | 3.16 GB | 14.5796 +/- 0.13395 | 66.075% |
|
|
|
|
| 23 |
(*Hellaswag scores here are not representative of real score since the questions were not randomized)
|
| 24 |
|
| 25 |
Note that this model ends up smaller than the Q4_0 from Bartowski. This is because llama.cpp sets some tensors to Q4_1 when quantizing models to Q4_0 with imatrix, but this is a static quant.
|
|
|
|
| 20 |
| [This model (older version)](https://huggingface.co/stduhpf/google-gemma-3-4b-it-qat-q4_0-gguf-small/blob/359d9494e5e9276e5c4aec2a9e0bdebd74310b1a/gemma-3-4b-it-q4_0_s.gguf) | 2.36 GB | 14.5943 +/- 0.13405 | 65.675% |
|
| 21 |
| [Q4_0 (bartowski)](https://huggingface.co/bartowski/google_gemma-3-1b-it-GGUF/blob/main/google_gemma-3-4b-it-Q4_0.gguf) | 2.37 GB | 16.8002 +/- 0.16519 | 65.65% |
|
| 22 |
| [QAT Q4_0 (google)](https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-gguf/blob/main/gemma-3-4b-it-q4_0.gguf) | 3.16 GB | 14.5796 +/- 0.13395 | 66.075% |
|
| 23 |
+
|
| 24 |
(*Hellaswag scores here are not representative of real score since the questions were not randomized)
|
| 25 |
|
| 26 |
Note that this model ends up smaller than the Q4_0 from Bartowski. This is because llama.cpp sets some tensors to Q4_1 when quantizing models to Q4_0 with imatrix, but this is a static quant.
|