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/MaziyarPanahi/gemma-3-1b-it-GGUF:Q3_K_Sollama · Q3_K_S · 0.6 GiB · quantizer (MaziyarPanahi)
hf.co/MaziyarPanahi/gemma-3-1b-it-GGUF:Q2_Kollama · Q2_K · 0.6 GiB · quantizer (MaziyarPanahi)
mlx-community/gemma-3-1b-it-qat-4bitmlx · 4BIT · 0.7 GiB · quantizer (mlx-community)
hf.co/lmstudio-community/gemma-3-1b-it-GGUF:Q3_K_Lollama · Q3_K_L · 0.7 GiB · quantizer (lmstudio-community)
hf.co/ggml-org/gemma-3-1b-it-GGUF:Q4_K_Mollama · Q4_K_M · 0.8 GiB · quantizer (ggml-org)
hf.co/lmstudio-community/gemma-3-1b-it-GGUF:Q6_Kollama · Q6_K · 0.9 GiB · quantizer (lmstudio-community)
hf.co/ggml-org/gemma-3-1b-it-GGUF:Q8_0ollama · Q8_0 · 1.0 GiB · quantizer (ggml-org)
hf.co/ggml-org/gemma-3-1b-it-GGUF:F16ollama · F16 · 1.9 GiB · quantizer (ggml-org)