Raises estimated decode speed by about 597%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Pixtral 12B needs ~41.3 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~10 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
24.1 tok/s
TTFT
8048 ms
Safe context
131K
Memory
24.0 GB / 108.8 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 24.1 tok/s | 4390 ms | 131K |
| Coding | F | Too heavy | 4.0 tok/s | 48065 ms | 4K |
| Agentic Coding | B | Runs well | 24.1 tok/s | 11706 ms | 131K |
| Reasoning | B | Runs well | 24.1 tok/s | 9511 ms | 131K |
| RAG | B | Runs well | 24.1 tok/s | 14633 ms | 131K |
How Pixtral 12B (12B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 4.7 GB | Low | B63 |
Q3_K_S | 3 | 5.9 GB | Low | B63 |
NVFP4 | 4 |
Copy-paste commands to run Pixtral 12B on your machine.
Run
ollama run pixtralUpgrade options
Raises estimated decode speed by about 597%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Raises estimated decode speed by about 597%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Raises estimated decode speed by about 597%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Pixtral 12B at F16 quantization (Runs well). The recommended Q4_K_M requires 11.0 GB which exceeds available memory, but at F16 it needs only 41.3 GB. Expected decode speed: 10.0 tok/s.
Pixtral 12B (12B parameters) requires approximately 11.0 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 41.3 GB.
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 41.3 GB.
On NVIDIA DGX Spark 128GB, Pixtral 12B achieves approximately 10.0 tokens per second decode speed with a time-to-first-token of 19319ms using F16 quantization.
For coding workloads, Pixtral 12B on NVIDIA DGX Spark 128GB receives a F grade with 4.0 tok/s and 4K context.
On NVIDIA DGX Spark 128GB, Pixtral 12B can safely use up to 131K tokens of context at F16 quantization. The model's official context limit is 131K, 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/pixtral-12b-on-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
6.7 GB |
| Medium |
| B63 |
Q4_K_M | 4 | 7.3 GB | Medium | B63 |
Q5_K_M | 5 | 8.6 GB | High | B63 |
Q6_K | 6 | 9.8 GB | High | B63 |
Q8_0 | 8 | 12.8 GB | Very High | B63 |
F16Best for your GPU | 16 | 24.6 GB | Maximum | B65 |
Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.