Gemma on NVIDIA Ampere

Can I run Gemma 3 27B on an RTX 3060 12GB?

Not at Q4_K_M — it needs 17.5 GB against 10.5 GB available. You would need 2 of these cards.

Won't fit

17.5 GB of 10.5 GB · 167%
018 GB
Weights 15.6 GB
KV cache 1.1 GB
Runtime overhead 0.8 GB
Over the limit 7.0 GB

Short by 7.0 GB. You can run it with 34 of 62 layers on the RTX 3060 12GB and the rest in system RAM, at roughly 4.45 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation4.45tok/s
Prompt processing192tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Gemma 3 27B on a RTX 3060 12GB

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 51.0 GB 53.0 GB Won't fit 0.89
INT8 / W8A8 8.50 26.8 GB 28.7 GB Won't fit 1.94
Q8_0 (GGUF) 8.50 26.8 GB 28.7 GB Won't fit 1.94
FP8 (E4M3) 8.00 25.5 GB 27.4 GB Won't fit 2.07
Q6_K 6.56 20.9 GB 22.9 GB Won't fit 2.76
Q5_K_M 5.67 18.1 GB 20.0 GB Won't fit 3.44
Q5_K_S 5.52 17.6 GB 19.5 GB Won't fit 3.61
Q4_K_M 4.85 15.6 GB 17.5 GB Won't fit 4.45
AWQ 4-bit 4.25 15.5 GB 17.4 GB Won't fit 4.48
GPTQ 4-bit 4.25 15.5 GB 17.4 GB Won't fit 4.48
MXFP4 4.25 15.5 GB 17.4 GB Won't fit 4.48
Q4_K_S 4.58 14.8 GB 16.7 GB Won't fit 4.80
Q4_0 4.55 14.7 GB 16.6 GB Won't fit 4.95
IQ4_XS 4.25 13.8 GB 15.7 GB Won't fit 5.54
Q3_K_M 3.91 12.7 GB 14.7 GB Won't fit 6.49
IQ3_M 3.70 12.1 GB 14.0 GB Won't fit 7.23
IQ3_XXS 3.06 10.2 GB 12.1 GB Won't fit 11.8
Q2_K 2.63 8.9 GB 10.8 GB Won't fit 4K 19.0
IQ2_XXS 2.06 7.1 GB 9.1 GB Runs comfortably 24K 28.3
IQ1_M 1.75 6.2 GB 8.1 GB Runs comfortably 35K 32.1

Also worth checking