← Gemma 3
Gemma 3 logo

Gemma 3 27B

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 7.3 GB; 14 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 7.3 GB; 14 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.

  1. Linux, CPU only · 2 CPUs1 GB RAMnone
  2. NVIDIA GeForce RTX 3050 Laptop GPU4 GB on the cardnone
  3. NVIDIA GeForce GTX 16504 GB on the cardnone
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAMnone
  5. Windows, CPU only · 12 CPUs7 GB RAM1 of 8
  6. Apple silicon8 GB RAM1 of 8
  7. Apple M18 GB RAM1 of 8
  8. Mac, CPU only · 8 CPUs8 GB RAM1 of 8
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the card2 of 8
  10. Tesla T415 GB on the card3 of 8
  11. Intel(R) UHD Graphics 73016 GB RAM3 of 8
  12. Intel(R) Iris(R) Xe Graphics16 GB RAM3 of 8
  13. Apple M416 GB RAM3 of 8
  14. Apple M116 GB RAM3 of 8
  15. NVIDIA L422 GB on the card6 of 8
  16. 2× Tesla T429 GB on the card6 of 8
  17. Linux, CPU only · 4 CPUs31 GB RAM6 of 8
  18. NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the cardevery build
hf.co/unsloth/gemma-3-27b-it-GGUF:IQ1_Sollama · IQ1_S · 6.1 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-27b-it-GGUF:IQ2_XXSollama · IQ2_XXS · 7.3 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-27b-it-GGUF:IQ3_XXSollama · IQ3_XXS · 10.1 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-27b-it-GGUF:Q4_0ollama · Q4_0 · 14.5 GiB · quantizer (unsloth)
hf.co/unsloth/gemma-3-27b-it-GGUF:Q4_K_Mollama · Q4_K_M · 15.4 GiB · quantizer (unsloth)
gaunernst/gemma-3-27b-it-int4-awqvllm · AWQ · 17.2 GiB · quantizer (gaunernst)
hf.co/unsloth/gemma-3-27b-it-GGUF:Q8_0ollama · Q8_0 · 26.7 GiB · quantizer (unsloth)
unsloth/gemma-3-27b-it-GGUF:BF16llamacpp · BF16 · 50.3 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.

gemma-3-27b-it-GPTQ-4b-128gnot measuredgemma-3-27b-it-mlxnot measured