Mixtral 8x22B needs ~91.3 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With NVFP4 quantization, expect ~53 tok/s.
Operating mode
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.
Select quantization to explore
18.3 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
41.3 tok/s
TTFT
4692 ms
Safe context
4K
Memory
98.3 GB / 80.0 GB
Offload
20%
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.
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 9.8 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 42.5 tok/s | 2486 ms | 4K |
| Coding | F | Too heavy | 41.3 tok/s | 4692 ms | 4K |
| Agentic Coding | F | Too heavy | 39.0 tok/s | 7220 ms | 4K |
| Reasoning | F | Too heavy | 41.3 tok/s | 5545 ms | 4K |
| RAG | F | Too heavy | 39.0 tok/s | 9025 ms | 4K |
How Mixtral 8x22B (141B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 55.0 GB | Low | B61 |
Q3_K_S | 3 | 69.1 GB | Low | F0 |
NVFP4 | 4 | 79.0 GB | Medium | F0 |
Q4_K_M | 4 | 86.0 GB | Medium | F0 |
Q5_K_M | 5 | 101.5 GB | High | F0 |
Q6_K | 6 | 115.6 GB | High | F0 |
Q8_0 | 8 | 150.9 GB | Very High | F0 |
F16 | 16 | 289.0 GB | Maximum | F0 |
Copy-paste commands to run Mixtral 8x22B on your machine.
Run
ollama run mixtral:8x22bOpções de upgrade
RTX PRO 6000 Blackwell Workstation Edition 96GBOpção econômicaMakes 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.
~$9,999 MSRP
RTX PRO 6000 Blackwell Server Edition 96GBMelhor custo-benefícioMakes 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.
~$9,999 MSRP
NVIDIA H20 96GBUpgrade NVIDIAMakes 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
Yes, NVIDIA H100 80GB can run Mixtral 8x22B at NVFP4 quantization (Very compromised (needs ~9.8 GB host RAM)). The recommended Q4_K_M requires 98.3 GB which exceeds available memory, but at NVFP4 it needs only 91.3 GB. Expected decode speed: 53.4 tok/s.
Mixtral 8x22B (141B parameters) requires approximately 98.3 GB at Q4_K_M quantization. On NVIDIA H100 80GB, it fits at NVFP4 using 91.3 GB.
The recommended quantization is Q4_K_M, but on NVIDIA H100 80GB the best fitting quantization is NVFP4, which uses 91.3 GB.
On NVIDIA H100 80GB, Mixtral 8x22B achieves approximately 53.4 tokens per second decode speed with a time-to-first-token of 3628ms using NVFP4 quantization.
For coding workloads, Mixtral 8x22B on NVIDIA H100 80GB receives a F grade with 41.3 tok/s and 4K context.
On NVIDIA H100 80GB, Mixtral 8x22B can safely use up to 4K tokens of context at NVFP4 quantization. The model's official context limit is 66K, but available memory constrains the safe maximum.
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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/mixtral-8x22b-on-h100-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: