text model · Mistral · Windows
Can I run Mixtral 8x7B on AMD Ryzen AI Halo (128GB)?
Yes. Mixtral 8x7B runs on AMD Ryzen AI Halo (128GB) at Q4_K_M (~28.9 GB of ~96 GB usable).
Runs at Q4_K_M using ~28.9 GB of ~96 GB usable. You have room for FP16 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. AMD Ryzen AI Halo (128GB) leaves ~67.1 GB of headroom, room to step up to FP16 for higher quality.
- Q4_K_M needed
- ~28.9 GB
- Usable on device
- ~96 GB
- Device memory
- 128 GB
- Best quant
- Q4_K_M
Which quant fits
Run it
Pick your tool. All 3 load the same Q4_K_M weights.
ollama run mixtral:8x7b llama-cli -hf MaziyarPanahi/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M lms get MaziyarPanahi/Mixtral-8x7B-Instruct-v0.1-GGUF - 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
- Memory
- 128 GB unified
- Usable for weights
- ~96 GB
- Power draw
- ~120 W
- Best runtime
- llama.cpp (Vulkan/ROCm) / LM Studio
You could also run
Run Mixtral 8x7B on other hardware
FAQ
Can AMD Ryzen AI Halo (128GB) run Mixtral 8x7B?
Yes. Mixtral 8x7B runs on AMD Ryzen AI Halo (128GB) at Q4_K_M (~28.9 GB of ~96 GB usable).
How much memory does Mixtral 8x7B need?
AMD Ryzen AI Halo (128GB) has room to spare. 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.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/mixtral-8x7b/amd-ryzen-ai-halo-128gb) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.