Skip to content
localmodel.run

text model · mistral · Windows

Can I run Mixtral 8x7B on Nvidia GeForce RTX 5090 (32GB)?

Compatibility verdict VRAM threshold engine
Yes, but tightGPU accelerated

Yes. Mixtral 8x7B runs on Nvidia GeForce RTX 5090 (32GB) at Q4_K_M (~28.9 GB of ~31 GB usable).

Needs ~28.9 GB Device usable ~31 GB

Fits at Q4_K_M (~28.9 GB of ~31 GB usable) but with little headroom, close other apps.

Q4_K_M needed
~28.9 GB
Usable on device
~31 GB
Device memory
32 GB
Best quant
Q4_K_M

Run it

Install commands Windows

Pick your tool. All three load the same Q4_K_M weights.

Ollama
$ ollama run mixtral:8x7b
llama.cpp
$ llama-cli -hf MaziyarPanahi/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
LM Studio
$ lms get MaziyarPanahi/Mixtral-8x7B-Instruct-v0.1-GGUF

AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Model mistral
Parameters
46.7B (MoE, 12.9B active)
Q4_K_M size
26.49 GB
Q8_0 size
46.22 GB
Context
32k
Ollama tag
mixtral:8x7b
Full Mixtral 8x7B requirements →
Device Windows
Memory
32 GB vram
Usable for weights
~31 GB
Best runtime
vLLM (Linux) / Ollama (CUDA)
Best models for Nvidia GeForce RTX 5090 (32GB) →

You could also run

Run Mixtral 8x7B on other hardware

FAQ

Can Nvidia GeForce RTX 5090 (32GB) run Mixtral 8x7B?

Yes. Mixtral 8x7B runs on Nvidia GeForce RTX 5090 (32GB) at Q4_K_M (~28.9 GB of ~31 GB usable).

How much memory does Mixtral 8x7B need?

It is a tight fit on Nvidia GeForce RTX 5090 (32GB). At Q4_K_M the weights are ~26.49 GB; with KV cache and runtime overhead, budget ~28.9 GB at a 4k context. It is a Mixture-of-Experts model (46.7B total / 12.9B active), so all experts must stay in memory; memory tracks total params, not active params.

What is the best tool to run Mixtral 8x7B on Windows?

LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Sources

Memory figures are estimates. See methodology.