Can the NVIDIA RTX 3070 run Mistral Nemo 12B?

RTX 3070 × Mistral Nemo 12B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M7.9 GB of 8 GB
Weights 6 GBKV cache 1.3 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Memory7.9 GBof 8 GB usable
Speed~45tokens 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

Only just. Mistral Nemo 12B fits on the NVIDIA RTX 3070 at Q3_K_M, which costs noticeable quality. Expect about 45 tokens/second. A card with more memory is a better experience.

Run it with Ollama

Ollama's default mistral-nemo:12b download is Q4_K_M, which needs about 9.3 GB, more than the 8 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

Run it in the cloud

Want full quality? Run Mistral Nemo 12B on a bigger rented GPU.

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

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 8 GB the NVIDIA RTX 3070 can use.

QuantQualityMemoryFits?Speed
FP16Full quality26.3 GBToo big—
Q8_0Near-lossless14.9 GBToo big—
Q6_KExcellent11.9 GBToo big—
Q5_K_MVery good10.6 GBToo big—
Q4_K_MGood, most popular9.3 GBToo big—
Q3_K_MNoticeably degraded7.9 GBFits~45 tok/s
Q2_KHeavily degraded6.5 GBFits~59 tok/s

Frequently asked questions

Can NVIDIA RTX 3070 run Mistral Nemo 12B?

Only just. Mistral Nemo 12B fits on the NVIDIA RTX 3070 at Q3_K_M, which costs noticeable quality. Expect about 45 tokens/second. A card with more memory is a better experience.

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 3070?

Roughly 45 tokens per second at Q3_K_M, estimated from the NVIDIA RTX 3070's 448 GB/s memory bandwidth.