Mixtral 8x22B needs ~103.1 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~63 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
Fit status
Runs well
Decode
62.6 tok/s
TTFT
3094 ms
Safe context
66K
Memory
103.1 GB / 128.0 GB
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 62.6 tok/s | 1687 ms | 66K |
| Coding | B | Runs well | 62.6 tok/s | 3094 ms | 66K |
| Agentic Coding | B | Tight fit | 62.6 tok/s | 4500 ms | 66K |
| Reasoning | B | Runs well | 62.6 tok/s | 3656 ms | 66K |
| RAG | B | Tight fit | 62.6 tok/s | 5625 ms | 66K |
How Mixtral 8x22B (141B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 55.0 GB | Low | B59 |
Q3_K_S | 3 | 69.1 GB | Low | B61 |
NVFP4 | 4 | 79.0 GB | Medium | B61 |
Q4_K_M | 4 | 86.0 GB | Medium | B61 |
Q5_K_MBest for your GPU | 5 | 101.5 GB | High | B61 |
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:8x22bUpgrade-Optionen
NVIDIA H200 141GBGünstige WahlRaises estimated decode speed by about 56%.
Moves you onto CUDA, which still has the broadest local-AI runtime coverage.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
ca. $30,000 MSRP
NVIDIA H200 PCIe 141GBBestes Preis-Leistungs-VerhältnisRaises estimated decode speed by about 56%.
Moves you onto CUDA, which still has the broadest local-AI runtime coverage.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
ca. $30,000 MSRP
Yes, Gaudi 3 128GB can run Mixtral 8x22B with a B grade (Runs well). Expected decode speed: 62.6 tok/s.
Mixtral 8x22B (141B parameters) requires approximately 103.1 GB of memory with Q4_K_M quantization.
The recommended quantization for Mixtral 8x22B is Q4_K_M, which balances quality and memory efficiency.
On Gaudi 3 128GB, Mixtral 8x22B achieves approximately 62.6 tokens per second decode speed with a time-to-first-token of 3094ms using Q4_K_M quantization.
For coding workloads, Mixtral 8x22B on Gaudi 3 128GB receives a B grade with 62.6 tok/s and 66K context.
On Gaudi 3 128GB, 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.
Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/mixtral-8x22b-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: