Rent a GPU

Can the NVIDIA RTX 4090 run Gemma 2 27B?

RTX 4090 × Gemma 2 27B8K context
YesRuns fully on the GPU
Memory at Q5_K_M23 GB of 24 GB
Weights 19.3 GBKV cache 3.1 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Memory23 GBof 24 GB usable
Speed~31tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 4090 can run Gemma 2 27B fully in VRAM at Q5_K_M (very good), using about 23 GB of the 24 GB available, at roughly 31 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Gemma 2 27B:

ollama run gemma2:27b

Ollama's default download is Q4_K_M (about 20.2 GB here). You have room for Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 4090? Run Gemma 2 27B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 24 GB the NVIDIA RTX 4090 can use.

QuantQualityMemoryFits?Speed
FP16Full quality58.1 GBToo big—
Q8_0Near-lossless32.6 GBToo big—
Q6_KExcellent26 GBToo big—
Q5_K_MVery good23 GBFits~31 tok/s
Q4_K_MGood, most popular20.2 GBFits~37 tok/s
Q3_K_MNoticeably degraded17 GBFits~45 tok/s
Q2_KHeavily degraded13.9 GBFits~59 tok/s

GPUs that run Gemma 2 27B comfortably

Models that run well on the NVIDIA RTX 4090

Frequently asked questions

Can NVIDIA RTX 4090 run Gemma 2 27B?

Yes. The NVIDIA RTX 4090 can run Gemma 2 27B fully in VRAM at Q5_K_M (very good), using about 23 GB of the 24 GB available, at roughly 31 tokens/second.

How much VRAM does Gemma 2 27B need?

About 20.2 GB at Q4_K_M with 8,192 tokens of context, and about 58.1 GB at full FP16 precision.

How fast is Gemma 2 27B on the NVIDIA RTX 4090?

Roughly 31 tokens per second at Q5_K_M, estimated from the NVIDIA RTX 4090's 1008 GB/s memory bandwidth.