Skip to content
Run LLM Locally

Mixtral 8x7B Instruct on the RTX 5090

With 32 GB of VRAM, the RTX 5090 runs Mixtral 8x7B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 27.5 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Mixtral 8x7B Instruct

Q4_K_M · 8K context

Compatible

The model needs about 27.5 GB and fits in the 31 GB available (3.5 GB left).

Your hardware
RTX 5090 32 GB · 64 GB RAM
Estimated memory
~27.5 GB estimate
VRAM (usable memory)
31 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
103–154 tok/s estimate
Largest context in fast memory
32K tokens
Confidence: low

Based on: memory bandwidth (1,792 GB/s) and model size

Memory breakdown

~27.5 GB (26.8 GB–28.3 GB) needed · estimate

Fits entirely in VRAM · 3.5 GB left

  • Model weights24.6 GB
  • KV cache1 GB
  • Runtime overhead0.6 GB
  • Safety margin1.3 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · flash attention on · weights = real file size

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • no benchmark for this hardware and model yet
  • mixture-of-experts: speed depends on expert routing

Other quantizations on the RTX 5090

Mixtral 8x7B Instruct on RTX 5090 + 64 GB RAM · 8K context
Mixtral 8x7B Instruct Q8_08K~50.2 GB · 3.5–6.5 tok/s estimateCPU/GPU offload
Mixtral 8x7B Instruct Q6_K8K~39.2 GB · 7.5–15 tok/s estimateCPU/GPU offload
Mixtral 8x7B Instruct Q5_K_M8K~33.2 GB · 23–44 tok/s estimateCPU/GPU offload
Mixtral 8x7B Instruct Q4_K_M8K~27.5 GB · 103–154 tok/s estimateCompatible
Mixtral 8x7B Instruct IQ4_XS8K~27.1 GB · 104–156 tok/s estimateCompatible
Mixtral 8x7B Instruct Q3_K_M8K~21.6 GB · 122–186 tok/s estimateExcellent

Alternatives

GPUs that run Mixtral 8x7B Instruct Q4_K_M entirely in VRAM

Other models that fit the RTX 5090

Where to buy a RTX 5090

Prices and links follow the market you choose.

GeForce RTX 5090

32 GB GDDR7 · 1,792 GB/s · 575 W

CompatibleRuns Mixtral 8x7B Instruct Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the RTX 5090 run Mixtral 8x7B Instruct?
The model needs about 27.5 GB and fits in the 31 GB available (3.5 GB left).
Which quantization should I use on the RTX 5090?
Q4_K_M is the highest-precision quantization that fits entirely in VRAM at 8K context. ~27.5 GB / 31 GB.
What is the largest context on the RTX 5090?
At Q4_K_M, about 32K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Mixtral 8x7B Instruct (RTX 5090)?
We estimate 103–154 tok/s (estimate, confidence low). Based on: memory bandwidth (1,792 GB/s) and model size.