Gemma 3 12B
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.
Be the first to measure it It needs about 3.4 GB; 17 of 18 kinds of machine on the network can hold it. The first machine to sign a result takes 10 points on the providers board.What is measured in Gemma 3 The members of this family that machines have already run, with their speed, price and context.
What it fits on
The smallest build needs about 3.4 GB; 17 of 18 kinds of machine on the network can hold it. Bars: each kind's memory (its card's, else RAM) · ticks: every build, at the size it held plus a fifth for the prompt.
- Linux, CPU only · 2 CPUs1 GB RAMnone
- NVIDIA GeForce RTX 3050 Laptop GPU4 GB on the card1 of 9
- NVIDIA GeForce GTX 16504 GB on the card1 of 9
- AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAM3 of 9
- Windows, CPU only · 12 CPUs7 GB RAM3 of 9
- Apple silicon8 GB RAM4 of 9
- Apple M18 GB RAM4 of 9
- Mac, CPU only · 8 CPUs8 GB RAM4 of 9
- NVIDIA GeForce RTX 3080 Ti12 GB on the card7 of 9
- Tesla T415 GB on the card8 of 9
- Intel(R) UHD Graphics 73016 GB RAM8 of 9
- Intel(R) Iris(R) Xe Graphics16 GB RAM8 of 9
- Apple M416 GB RAM8 of 9
- Apple M116 GB RAM8 of 9
- NVIDIA L422 GB on the card8 of 9
- 2× Tesla T429 GB on the cardevery build
- Linux, CPU only · 4 CPUs31 GB RAMevery build
- NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the cardevery build
hf.co/unsloth/gemma-3-12b-it-qat-GGUF:IQ1_Sollama · IQ1_S · 2.8 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-12b-it-qat-GGUF:IQ2_XXSollama · IQ2_XXS · 3.4 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-12b-it-qat-GGUF:IQ3_XXSollama · IQ3_XXS · 4.5 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-12b-it-qat-GGUF:Q4_0ollama · Q4_0 · 6.4 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-12b-it-qat-GGUF:Q4_K_Mollama · Q4_K_M · 6.8 GiB · quantizer (unsloth)
abhishekchohan/gemma-3-12b-it-quantized-W4A16vllm · W4A16 · 7.8 GiB · quantizer (abhishekchohan)
gaunernst/gemma-3-12b-it-int4-awqvllm · AWQ · 8.5 GiB · quantizer (gaunernst)
hf.co/unsloth/gemma-3-12b-it-qat-GGUF:Q8_0ollama · Q8_0 · 11.7 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-12b-it-qat-GGUF:BF16ollama · BF16 · 21.9 GiB · quantizer (unsloth)
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.