TranslateGemma 4B

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-4b-it-GGUF:Q2_Kollama · Q2_K · 1.6 GiB · quantizer (mradermacher)

hf.co/mradermacher/translategemma-4b-it-GGUF:Q3_K_Sollama · Q3_K_S · 1.8 GiB · quantizer (mradermacher)

mlx-community/translategemma-4b-it-4bitmlx · 4BIT · 2.0 GiB · quantizer (mlx-community)

hf.co/bullerwins/translategemma-4b-it-GGUF:Q3_K_Lollama · Q3_K_L · 2.1 GiB · quantizer (bullerwins)

hf.co/bullerwins/translategemma-4b-it-GGUF:Q4_K_Sollama · Q4_K_S · 2.2 GiB · quantizer (bullerwins)

hf.co/bullerwins/translategemma-4b-it-GGUF:Q4_K_Mollama · Q4_K_M · 2.3 GiB · quantizer (bullerwins)

mlx-community/translategemma-4b-it-8bitmlx · 8BIT · 3.8 GiB · quantizer (mlx-community)

hf.co/bullerwins/translategemma-4b-it-GGUF:Q8_0ollama · Q8_0 · 3.8 GiB · quantizer (bullerwins)

hf.co/mradermacher/translategemma-4b-it-GGUF:F16ollama · F16 · 7.2 GiB · quantizer (mradermacher)

derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

translategemma-4b-it-4bit_immersive-translatenot measured translategemma-4b-it-novisionnot measured vllm-translategemma-4b-itnot measured translategemma-4b-it-4bit_immersive-translatenot measured translategemma-4b-it-i1-GGUFnot measured translategemma-text-4b-it-ONNXnot measured