No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.
hf.co/mradermacher/translategemma-12b-it-GGUF:Q2_Kollama · Q2_K · 4.4 GiB · quantizer (mradermacher)
hf.co/mradermacher/translategemma-12b-it-GGUF:Q3_K_Sollama · Q3_K_S · 5.1 GiB · quantizer (mradermacher)
hf.co/mradermacher/translategemma-12b-it-GGUF:Q3_K_Lollama · Q3_K_L · 6.0 GiB · quantizer (mradermacher)
mlx-community/translategemma-12b-it-4bitmlx · 4BIT · 6.2 GiB · quantizer (mlx-community)
hf.co/mradermacher/translategemma-12b-it-GGUF:Q4_K_Sollama · Q4_K_S · 6.5 GiB · quantizer (mradermacher)
hf.co/mradermacher/translategemma-12b-it-GGUF:Q4_K_Mollama · Q4_K_M · 6.8 GiB · quantizer (mradermacher)
mlx-community/translategemma-12b-it-6bitmlx · 6BIT · 8.9 GiB · quantizer (mlx-community)
kaitchup/translategemma-12b-it-NVFP4vllm · W4A4 · 10.2 GiB · quantizer (kaitchup)
mlx-community/translategemma-12b-it-8bitmlx · 8BIT · 11.6 GiB · quantizer (mlx-community)
hf.co/mradermacher/translategemma-12b-it-GGUF:Q8_0ollama · Q8_0 · 11.7 GiB · quantizer (mradermacher)
kaitchup/translategemma-12b-it-FP8-Dynamicvllm · FP8 · 12.7 GiB · quantizer (kaitchup)