Can Mixtral 8x22B run on AMD Instinct MI210 64GB?

YES — With Q2_K

B63Good

○Estimated from fit model

Mixtral 8x22B needs ~65.7 GB VRAM. AMD Instinct MI210 64GB has 64.0 GB. With Q2_K quantization, expect ~25 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Mixtral 8x22B at Q4_K_M needs 96.7 GB — too much for AMD Instinct MI210 64GB (64.0 GB). Runs at Q2_K (65.7 GB) with low quality.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 96.7 GB, exceeds 64.0 GB available

96.7 GB required64.0 GB available

151% VRAM needed

32.7 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

8.5 tok/s

TTFT

22880 ms

Safe context

Memory

96.7 GB / 64.0 GB

Offload

30%

Memory breakdown

Weights86.0 GB

KV Cache3.4 GB

Runtime0.9 GB

Headroom6.4 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsMixtral 8x22B on AMD Instinct MI210 64GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
 - Speed = 60 mph (miles per hour)
 - Time = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
 Distance = 60 mph x 2.5 h
 = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
 - First half: 1.25 hours at 60 mph = 75 miles
 - Stop: 20 minutes (no distance)
 - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 8.5 tok/s decode · 22.9s TTFT (warm) · 21 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	8.8 tok/s	12020 ms	4K
Coding	F	Too heavy	7.8 tok/s	24787 ms	4K
Agentic Coding	F	Too heavy	7.9 tok/s	35804 ms	4K
Reasoning	F	Too heavy	8.5 tok/s	27040 ms	4K
RAG	F	Too heavy	7.9 tok/s	44755 ms	4K

Quantization options

How Mixtral 8x22B (141B params) fits at each quantization level on AMD Instinct MI210 64GB (64.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	55.0 GB	Low	F0
Q3_K_S	3	69.1 GB	Low	F0
NVFP4	4

Get started

Copy-paste commands to run Mixtral 8x22B on your machine.

Run

ollama run mixtral:8x22b

Upgrade options

Hardware that runs Mixtral 8x22B well

AMD Instinct MI350X 288GBBudget pick

288 GB VRAM (+224)8000 GB/s (+6362)

Makes the model fit on the accelerator instead of staying completely out of reach.141.1 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$8,000 MSRP

AMD Instinct MI300A 128GBBest value

128 GB VRAM (+64)5300 GB/s (+3662)

Makes the model fit on the accelerator instead of staying completely out of reach.89.6 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$12,000 MSRP

AMD Instinct MI250X 128GBAMD upgrade

128 GB VRAM (+64)3200 GB/s (+1562)

Makes the model fit on the accelerator instead of staying completely out of reach.60.3 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$15,000 MSRP

Frequently asked questions

See all results for AMD Instinct MI210 64GB See all hardware for Mixtral 8x22B

URL: https://willitrunai.com/can-run/mixtral-8x22b-on-instinct-mi210-64gb

⇱

Can Mixtral 8x22B run on AMD Instinct MI210 64GB?

YES — With Q2_K

Choose the run profile you care about

Memory breakdown

See how fast it feels

What limits this setup

Best improvement path

Performance by workload

Quantization options

Get started

Hardware that runs Mixtral 8x22B well

Frequently asked questions