Mistral Small 4 119B needs ~91.7 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~113 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
112.9 tok/s
TTFT
1715 ms
Safe context
124K
Memory
91.7 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 | S | Runs well | 112.9 tok/s | 935 ms | 124K |
| Coding | S | Runs well | 112.9 tok/s | 1715 ms | 124K |
| Agentic Coding | S | Runs well | 112.9 tok/s | 2494 ms | 124K |
| Reasoning | S | Runs well | 112.9 tok/s | 2027 ms | 124K |
| RAG | S | Runs well | 112.9 tok/s | 3118 ms | 124K |
How Mistral Small 4 119B (119B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 46.4 GB | Low | A85 |
Q3_K_S | 3 | 58.3 GB | Low | S87 |
NVFP4 | 4 |
Copy-paste commands to run Mistral Small 4 119B on your machine.
Run
lms load Mistral-Small-4-119B-2603 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 37.5 tok/s | ||
| 122B | S |
Yes, Gaudi 3 128GB can run Mistral Small 4 119B with a S grade (Runs well). Expected decode speed: 112.9 tok/s.
Mistral Small 4 119B (119B parameters) requires approximately 91.7 GB of memory with Q4_K_M quantization.
The recommended quantization for Mistral Small 4 119B is Q4_K_M, which balances quality and memory efficiency.
On Gaudi 3 128GB, Mistral Small 4 119B achieves approximately 112.9 tokens per second decode speed with a time-to-first-token of 1715ms using Q4_K_M quantization.
For coding workloads, Mistral Small 4 119B on Gaudi 3 128GB receives a S grade with 112.9 tok/s and 124K context.
On Gaudi 3 128GB, Mistral Small 4 119B can safely use up to 124K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/mistral-small-4-119b-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:
66.6 GB |
| Medium |
| S88 |
Q4_K_M | 4 | 72.6 GB | Medium | S88 |
Q5_K_M | 5 | 85.7 GB | High | S88 |
Q6_KBest for your GPU | 6 | 97.6 GB | High | S88 |
Q8_0 | 8 | 127.3 GB | Very High | F0 |
F16 | 16 | 244.0 GB | Maximum | F0 |
| 104.1 tok/s |
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.