Codestral 2 25.08 needs ~29.6 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~195 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
195.0 tok/s
TTFT
993 ms
Safe context
256K
Memory
29.6 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 | A | Runs well | 195.0 tok/s | 541 ms | 256K |
| Coding | A | Runs well | 195.0 tok/s | 993 ms | 256K |
| Agentic Coding | A | Runs well | 195.0 tok/s | 1444 ms | 256K |
| Reasoning | A | Runs well | 195.0 tok/s | 1173 ms | 256K |
| RAG | A | Runs well | 195.0 tok/s | 1805 ms | 256K |
How Codestral 2 25.08 (22B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | A73 |
Q3_K_S | 3 | 10.8 GB | Low | A73 |
NVFP4 | 4 | 12.3 GB | Medium | A73 |
Q4_K_M | 4 | 13.4 GB | Medium | A73 |
Q5_K_M | 5 | 15.8 GB | High | A73 |
Q6_K | 6 | 18.0 GB | High | A73 |
Q8_0 | 8 | 23.5 GB | Very High | A74 |
F16Best for your GPU | 16 | 45.1 GB | Maximum | A77 |
Copy-paste commands to run Codestral 2 25.08 on your machine.
Run
lms load codestral-2508 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Devstral 2 123B Instruct | 123B | S | 37.5 tok/s | |
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 391.6 tok/s | |
| Qwen 3.5 27B | 27B | S | 169.8 tok/s | |
| Qwen 3.6 27B | 27B | S | 105.9 tok/s | |
| Qwen 3.5 122B A10B | 122B | S | 104.1 tok/s |
Yes, Gaudi 3 128GB can run Codestral 2 25.08 with a A grade (Runs well). Expected decode speed: 195.0 tok/s.
Codestral 2 25.08 (22B parameters) requires approximately 29.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral 2 25.08 is Q4_K_M, which balances quality and memory efficiency.
On Gaudi 3 128GB, Codestral 2 25.08 achieves approximately 195.0 tokens per second decode speed with a time-to-first-token of 993ms using Q4_K_M quantization.
For coding workloads, Codestral 2 25.08 on Gaudi 3 128GB receives a A grade with 195.0 tok/s and 256K context.
On Gaudi 3 128GB, Codestral 2 25.08 can safely use up to 256K tokens of context. The model's official context limit is 256K, 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/codestral-2-25.08-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: