Can Mixtral 8x7B run on AMD Instinct MI100 32GB?

BARELY — Tight on Memory

B56Good

○Estimated from fit model

Mixtral 8x7B needs ~34.7 GB VRAM. AMD Instinct MI100 32GB has 32.0 GB. With Q4_K_M quantization, expect ~36 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload

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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 34.7 GB, 36.3 tok/s, Very compromised (needs ~2.2 GB host RAM)

34.7 GB required32.0 GB available

108% VRAM needed

2.7 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~2.2 GB host RAM)

Decode

36.3 tok/s

TTFT

5339 ms

Safe context

Memory

34.7 GB / 32.0 GB

Offload

10%

Memory breakdown

Weights28.7 GB

KV Cache2.0 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsMixtral 8x7B on AMD Instinct MI100 32GB
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: 36.3 tok/s decode · 5.3s TTFT (warm) · 91 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

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

Increase host RAM if you keep offloading

This setup may need roughly 2.2 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs with offload (needs ~1.5 GB host RAM)	38.5 tok/s	2743 ms	4K
Coding	B	Very compromised (needs ~2.2 GB host RAM)	36.3 tok/s	5339 ms	4K
Agentic Coding	B	Very compromised (needs ~3.7 GB host RAM)	32.3 tok/s	8714 ms	4K
Reasoning	B	Very compromised (needs ~2.2 GB host RAM)	36.3 tok/s	6310 ms	4K
RAG	B	Very compromised (needs ~3.7 GB host RAM)	32.3 tok/s