Gemma on NVIDIA Blackwell

Can I run Gemma 3 27B on an RTX 5080?

Not at Q4_K_M — it needs 17.5 GB against 14.2 GB available. Drop to IQ3_M and it fits, at about 48.5 tokens per second.

Won't fit

17.5 GB of 14.2 GB · 123%
018 GB
Weights 15.6 GB
KV cache 1.1 GB
Runtime overhead 0.8 GB
Over the limit 3.3 GB

Short by 3.3 GB. You can run it with 48 of 62 layers on the RTX 5080 and the rest in system RAM, at roughly 9.29 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation9.29tok/s
Prompt processing858tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Gemma 3 27B on a RTX 5080

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 1.03
INT8 / W8A8 8.50 26.8 GB 28.7 GB Won't fit 2.65
Q8_0 (GGUF) 8.50 26.8 GB 28.7 GB Won't fit 2.65
FP8 (E4M3) 8.00 25.5 GB 27.4 GB Won't fit 2.85
Q6_K 6.56 20.9 GB 22.9 GB Won't fit 4.25
Q5_K_M 5.67 18.1 GB 20.0 GB Won't fit 6.08
Q5_K_S 5.52 17.6 GB 19.5 GB Won't fit 6.51
Q4_K_M 4.85 15.6 GB 17.5 GB Won't fit 9.29
AWQ 4-bit 4.25 15.5 GB 17.4 GB Won't fit 9.88
GPTQ 4-bit 4.25 15.5 GB 17.4 GB Won't fit 9.88
MXFP4 4.25 15.5 GB 17.4 GB Won't fit 9.88
Q4_K_S 4.58 14.8 GB 16.7 GB Won't fit 11.7
Q4_0 4.55 14.7 GB 16.6 GB Won't fit 12.6
IQ4_XS 4.25 13.8 GB 15.7 GB Won't fit 16.8
Q3_K_M 3.91 12.7 GB 14.7 GB Won't fit 3K 27.8
IQ3_M 3.70 12.1 GB 14.0 GB Fits, but tight 10K 48.5
IQ3_XXS 3.06 10.2 GB 12.1 GB Runs comfortably 33K 57.0
Q2_K 2.63 8.9 GB 10.8 GB Runs comfortably 48K 64.5
IQ2_XXS 2.06 7.1 GB 9.1 GB Runs comfortably 68K 78.2
IQ1_M 1.75 6.2 GB 8.1 GB Runs comfortably 79K 88.4

Also worth checking