Raises estimated decode speed by about 268%.
Adds memory headroom for longer context windows and future model growth.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
~$1,999 MSRP
Codestral 22B needs ~19.2 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~18 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
19.7 tok/s
TTFT
9815 ms
Safe context
33K
Memory
19.2 GB / 24.0 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 | 18.3 tok/s | 5755 ms | 33K |
| Coding | B | Runs well | 18.3 tok/s | 10551 ms | 33K |
| Agentic Coding | B | Tight fit | 18.3 tok/s | 15347 ms | 33K |
| Reasoning | B | Runs well | 18.3 tok/s | 12470 ms | 33K |
| RAG | B | Tight fit | 18.3 tok/s | 19184 ms | 33K |
How Codestral 22B (22B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.6 GB | Low | B58 |
Q3_K_S | 3 | 10.8 GB | Low | B60 |
NVFP4 | 4 |
Copy-paste commands to run Codestral 22B on your machine.
Run
ollama run codestralUpgrade options
Raises estimated decode speed by about 268%.
Adds memory headroom for longer context windows and future model growth.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
~$1,999 MSRP
Raises estimated decode speed by about 191%.
Adds memory headroom for longer context windows and future model growth.
This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.
~$2,499 MSRP
Yes, Intel Arc Pro B60 24GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 18.3 tok/s.
Codestral 22B (22B parameters) requires approximately 19.2 GB of memory with Q4_K_M quantization.
The recommended quantization for Codestral 22B is Q4_K_M, which balances quality and memory efficiency.
On Intel Arc Pro B60 24GB, Codestral 22B achieves approximately 18.3 tokens per second decode speed with a time-to-first-token of 10551ms using Q4_K_M quantization.
For coding workloads, Codestral 22B on Intel Arc Pro B60 24GB receives a B grade with 18.3 tok/s and 33K context.
On Intel Arc Pro B60 24GB, Codestral 22B can safely use up to 33K tokens of context. The model's official context limit is 33K, 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/codestral-22b-on-arc-pro-b60-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
12.3 GB |
| Medium |
| B60 |
Q4_K_M | 4 | 13.4 GB | Medium | B60 |
Q5_K_M | 5 | 15.8 GB | High | B60 |
Q6_KBest for your GPU | 6 | 18.0 GB | High | B59 |
Q8_0 | 8 | 23.5 GB | Very High | F0 |
F16 | 16 | 45.1 GB | Maximum | F0 |
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.