willitrun·ai

Can Mixtral 8x22B run on NVIDIA H200 141GB?

YES — Runs Great

A70Great
Estimated from fit model

Mixtral 8x22B needs ~104.4 GB VRAM. NVIDIA H200 141GB has 141.0 GB. With Q4_K_M quantization, expect ~97 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) — 104.4 GB, 97.4 tok/s, Runs well
104.4 GB required141.0 GB available
74% VRAM used

Fit status

Runs well

Decode

97.4 tok/s

TTFT

1987 ms

Safe context

66K

Memory

104.4 GB / 141.0 GB

Memory breakdown

Weights86.0 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom14.1 GB

See how fast it feels

See how fast it feelsMixtral 8x22B on NVIDIA H200 141GB
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: 97.4 tok/s decode · 2.0s TTFT (warm) · 244 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
ChatARuns well97.4 tok/s1084 ms66K
CodingARuns well97.4 tok/s1987 ms66K
Agentic CodingARuns well97.4 tok/s2890 ms66K
ReasoningARuns well97.4 tok/s2349 ms66K
RAGARuns well97.4 tok/s3613 ms66K

Inference speed

Mixtral 8x22B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Mixtral 8x22B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~14 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?
Mac Studio M3 Ultra 256GB
256 GBQ4_K_M13.5Fits
Mac Studio M2 Ultra 128GB
128 GBQ4_K_M9.2Heavy offload
Mac Studio M1 Ultra 128GB
128 GBQ4_K_M8.7Heavy offload
MacBook Pro M4 Max 128GB
128 GBQ4_K_M6.8Heavy offload
2× RX 7900 XTX 24GB
48 GBQ4_K_M5.0Too big
NVIDIARTX 5090 32GB
32 GBQ4_K_M3.9Too big
MacBook Pro M4 Max 64GB
64 GBQ4_K_M3.7Too big
NVIDIA2× RTX 4090 24GB
48 GBQ4_K_M3.4Too big
NVIDIA2× RTX 3090 24GB
48 GBQ4_K_M2.9Too big
MacBook Pro M3 Max 64GB
64 GBQ4_K_M2.6Too big
NVIDIA4× RTX 3060 12GB
48 GBQ4_K_M2.6Too big
NVIDIARTX 4090 24GB
24 GBQ4_K_M2.5Too big
RX 7900 XTX 24GB
24 GBQ4_K_M2.5Too big
MacBook Pro M1 Max 64GB
64 GBQ4_K_M2.4Too big
MacBook Pro M4 Pro 48GB
48 GBQ4_K_M2.3Too big
NVIDIARTX 3090 24GB
24 GBQ4_K_M2.1Too big
NVIDIARTX 4080 Super 16GB
16 GBQ4_K_M2.0Too big
NVIDIARTX 4070 12GB
12 GBQ4_K_M2.0Too big
NVIDIARTX 3060 12GB
12 GBQ4_K_M2.0Too big
NVIDIARTX 4060 8GB
8 GBQ4_K_M2.0Too 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 8x22B (141B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
55.0 GB
LowB58
Q3_K_S
3
69.1 GB
LowB60
NVFP4
4
79.0 GB
MediumB61
Q4_K_M
4
86.0 GB
MediumB61
Q5_K_M
5
101.5 GB
HighB61
Q6_KBest for your GPU
6
115.6 GB
HighB61
Q8_0
8
150.9 GB
Very HighF0
F16
16
289.0 GB
MaximumF0

Get started

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

Run

ollama run mixtral:8x22b

Your hardware

More models your NVIDIA H200 141GB can run

ModelParamsGradeDecodeCapabilities
AlibabaQwen 3 235B A22B235BA56.1 tok/s
MiniMax M2.7230BA65.2 tok/s

Frequently asked questions

Can NVIDIA H200 141GB run Mixtral 8x22B?

Yes, NVIDIA H200 141GB can run Mixtral 8x22B with a A grade (Runs well). Expected decode speed: 97.4 tok/s.

How much VRAM does Mixtral 8x22B need?

Mixtral 8x22B (141B parameters) requires approximately 104.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Mixtral 8x22B?

The recommended quantization for Mixtral 8x22B is Q4_K_M, which balances quality and memory efficiency.

What speed will Mixtral 8x22B run at on NVIDIA H200 141GB?

On NVIDIA H200 141GB, Mixtral 8x22B achieves approximately 97.4 tokens per second decode speed with a time-to-first-token of 1987ms using Q4_K_M quantization.

Can NVIDIA H200 141GB run Mixtral 8x22B for coding?

For coding workloads, Mixtral 8x22B on NVIDIA H200 141GB receives a A grade with 97.4 tok/s and 66K context.

What context window can Mixtral 8x22B use on NVIDIA H200 141GB?

On NVIDIA H200 141GB, Mixtral 8x22B can safely use up to 66K tokens of context. The model's official context limit is 66K, but available memory constrains the safe maximum.

See all results for NVIDIA H200 141GBSee all hardware for Mixtral 8x22B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/mixtral-8x22b-on-h200-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: