Rent a GPU

Can the NVIDIA RTX 4090 run Mistral Nemo 12B?

RTX 4090 × Mistral Nemo 12B8K context
YesRuns fully on the GPU
Memory at Q8_014.9 GB of 24 GB
Weights 13 GBKV cache 1.3 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Memory14.9 GBof 24 GB usable
Speed~47tokens 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 Mistral Nemo 12B fully in VRAM at Q8_0 (near-lossless), using about 14.9 GB of the 24 GB available, at roughly 47 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Mistral Nemo 12B:

ollama run mistral-nemo:12b

Ollama's default download is Q4_K_M (about 9.3 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 4090? Run Mistral Nemo 12B 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 quality26.3 GBToo big—
Q8_0Near-lossless14.9 GBFits~47 tok/s
Q6_KExcellent11.9 GBFits~60 tok/s
Q5_K_MVery good10.6 GBFits~70 tok/s
Q4_K_MGood, most popular9.3 GBFits~82 tok/s
Q3_K_MNoticeably degraded7.9 GBFits~101 tok/s
Q2_KHeavily degraded6.5 GBFits~132 tok/s

GPUs that run Mistral Nemo 12B comfortably

Models that run well on the NVIDIA RTX 4090

Frequently asked questions

Can NVIDIA RTX 4090 run Mistral Nemo 12B?

Yes. The NVIDIA RTX 4090 can run Mistral Nemo 12B fully in VRAM at Q8_0 (near-lossless), using about 14.9 GB of the 24 GB available, at roughly 47 tokens/second.

How much VRAM does Mistral Nemo 12B need?

About 9.3 GB at Q4_K_M with 8,192 tokens of context, and about 26.3 GB at full FP16 precision.

How fast is Mistral Nemo 12B on the NVIDIA RTX 4090?

Roughly 47 tokens per second at Q8_0, estimated from the NVIDIA RTX 4090's 1008 GB/s memory bandwidth.