Rent a GPU

Can the NVIDIA RTX 3090 Ti run Mixtral 8x7B?

RTX 3090 Ti × Mixtral 8x7B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K19.2 GB of 24 GB
Weights 17.5 GBKV cache 1.1 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~125tokens per second
Max context32Kthe model's full window
  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. Mixtral 8x7B fits on the NVIDIA RTX 3090 Ti at Q2_K, which costs noticeable quality. Expect about 125 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default mixtral:8x7b download is Q4_K_M, which needs about 30 GB, more than the 24 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the RTX 3090 Ti

Run it in the cloud

Want full quality? Run Mixtral 8x7B on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 3090 Ti can use.

QuantQualityMemoryFits?Speed
FP16Full quality95.1 GBToo big—
Q8_0Near-lossless51.3 GBToo big—
Q6_KExcellent40 GBToo big—
Q5_K_MVery good34.9 GBToo big—
Q4_K_MGood, most popular30 GBToo big—
Q3_K_MNoticeably degraded24.5 GBToo big—
Q2_KHeavily degraded19.2 GBFits~125 tok/s

Measured speed from real RTX 3090 Ti owners

Tokens per second that people measured on their own NVIDIA RTX 3090 Ti, next to our estimate.

No one has measured Mixtral 8x7B on the NVIDIA RTX 3090 Ti yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 3090 Ti? Add your real speed

One command times Mixtral 8x7B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- mixtral:8x7b

Windows (PowerShell)

$env:GPUFIT_MODEL="mixtral:8x7b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Mixtral 8x7B comfortably

Check Radeon AI PRO R9700 prices

Models that run well on the NVIDIA RTX 3090 Ti

Frequently asked questions

Can NVIDIA RTX 3090 Ti run Mixtral 8x7B?

Only just. Mixtral 8x7B fits on the NVIDIA RTX 3090 Ti at Q2_K, which costs noticeable quality. Expect about 125 tokens/second. A card with more memory is a better experience.

How much VRAM does Mixtral 8x7B need?

About 30 GB at Q4_K_M with 8,192 tokens of context, and about 95.1 GB at full FP16 precision.

How fast is Mixtral 8x7B on the NVIDIA RTX 3090 Ti?

Roughly 125 tokens per second at Q2_K, estimated from the NVIDIA RTX 3090 Ti's 1008 GB/s memory bandwidth.