dahus
/

gemma-4-e2b-it-q4-nf4

image-text-to-text

4-bit precision

Model card Files Files and versions

dahus commited on 13 days ago

Commit

2ded0f8

·

verified ·

1 Parent(s): 2d2e635

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ license: apache-2.0
-# Gemma 4 E2B — NF4 Quantization (bitsandbytes)
 Quantized version of [google/gemma-4-e2b-it](https://huggingface.co/google/gemma-4-e2b-it)
 using bitsandbytes NF4 (4-bit). Tested on RTX 5090 (Blackwell, sm_120).

+# Gemma 4 E2B it — NF4 Quantization (bitsandbytes)
 Quantized version of [google/gemma-4-e2b-it](https://huggingface.co/google/gemma-4-e2b-it)
 using bitsandbytes NF4 (4-bit). Tested on RTX 5090 (Blackwell, sm_120).