willitrun·ai

Can Mixtral 8x7B run on AMD Instinct MI350X 288GB?

YES — Runs Great

B62Good
Estimated from fit model

Mixtral 8x7B needs ~60.3 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~420 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced
Share:

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) — 60.3 GB, 420.1 tok/s, Runs well
60.3 GB required288.0 GB available
21% VRAM used

Fit status

Runs well

Decode

420.1 tok/s

TTFT

461 ms

Safe context

33K

Memory

60.3 GB / 288.0 GB

Memory breakdown

Weights28.7 GB
KV Cache2.0 GB
Runtime0.9 GB
Headroom28.8 GB

See how fast it feels

See how fast it feelsMixtral 8x7B on AMD Instinct MI350X 288GB
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: 420.1 tok/s decode · 461ms TTFT (warm) · 1050 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatBRuns well420.1 tok/s350 ms33K
CodingBRuns well420.1 tok/s461 ms33K
Agentic CodingBRuns well420.1 tok/s670 ms33K
ReasoningBRuns well420.1 tok/s545 ms33K
RAGBRuns well420.1 tok/s838 ms33K

Inference speed

Mixtral 8x7B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Mixtral 8x7B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is 2× RX 7900 XTX 24GB at ~85 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / MacMemoryQuantSpeed (tok/s)Fits?
2× RX 7900 XTX 24GB
48 GBQ4_K_M84.5Fits
NVIDIA2× RTX 4090 24GB
48 GBQ4_K_M77.1Fits
NVIDIA2× RTX 3090 24GB
48 GBQ4_K_M66.0Fits
NVIDIA4× RTX 3060 12GB
48 GBQ4_K_M58.1Fits
NVIDIARTX 5090 32GB
32 GBQ4_K_M54.9Heavy offload
Mac Studio M3 Ultra 256GB
256 GBQ4_K_M40.1Fits
Mac Studio M2 Ultra 128GB
128 GBQ4_K_M33.4Fits
Mac Studio M1 Ultra 128GB
128 GBQ4_K_M31.6Fits
MacBook Pro M4 Max 128GB
128 GBQ4_K_M24.7Fits
MacBook Pro M4 Max 64GB
64 GBQ4_K_M24.7Tight
NVIDIARTX 4090 24GB
24 GBQ4_K_M19.6Too big
RX 7900 XTX 24GB
24 GBQ4_K_M18.0Too big
MacBook Pro M3 Max 64GB
64 GBQ4_K_M17.3Tight
NVIDIARTX 3090 24GB
24 GBQ4_K_M16.7Too big
MacBook Pro M1 Max 64GB
64 GBQ4_K_M15.8Tight
MacBook Pro M4 Pro 48GB
48 GBQ4_K_M13.6Offloads
NVIDIARTX 4080 Super 16GB
16 GBQ4_K_M7.0Too big
NVIDIARTX 4070 12GB
12 GBQ4_K_M4.1Too big
NVIDIARTX 3060 12GB
12 GBQ4_K_M2.6Too big
NVIDIARTX 4060 8GB
8 GBQ4_K_M2.1Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Mixtral 8x7B (47B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
18.3 GB
LowC52
Q3_K_S
3
23.0 GB
LowC52
NVFP4
4
26.3 GB
MediumC53
Q4_K_M
4
28.7 GB
MediumC53
Q5_K_M
5
33.8 GB
HighC53
Q6_K
6
38.5 GB
HighC54
Q8_0
8
50.3 GB
Very HighC54
F16Best for your GPU
16
96.4 GB
MaximumB58

Get started

Copy-paste commands to run Mixtral 8x7B on your machine.

Run

ollama run mixtral

Frequently asked questions

Can AMD Instinct MI350X 288GB run Mixtral 8x7B?

Yes, AMD Instinct MI350X 288GB can run Mixtral 8x7B with a B grade (Runs well). Expected decode speed: 420.1 tok/s.

How much VRAM does Mixtral 8x7B need?

Mixtral 8x7B (47B parameters) requires approximately 60.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Mixtral 8x7B?

The recommended quantization for Mixtral 8x7B is Q4_K_M, which balances quality and memory efficiency.

What speed will Mixtral 8x7B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Mixtral 8x7B achieves approximately 420.1 tokens per second decode speed with a time-to-first-token of 461ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Mixtral 8x7B for coding?

For coding workloads, Mixtral 8x7B on AMD Instinct MI350X 288GB receives a B grade with 420.1 tok/s and 33K context.

What context window can Mixtral 8x7B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Mixtral 8x7B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GBSee all hardware for Mixtral 8x7B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/mixtral-8x7b-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: