Pixtral Large 124B needs ~121.0 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With Q6_K quantization, expect ~2 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
Tight fit
Decode
2.4 tok/s
TTFT
82208 ms
Safe context
57K
Memory
95.0 GB / 108.8 GB
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
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.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 10.3 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Tight fit | 2.4 tok/s | 44841 ms | 57K |
| Coding | F | Too heavy | 2.0 tok/s | 96800 ms | 4K |
| Agentic Coding | A | Tight fit | 2.4 tok/s | 119575 ms | 57K |
| Reasoning | A | Tight fit | 2.4 tok/s | 97155 ms | 57K |
| RAG | A | Tight fit | 2.4 tok/s | 149469 ms | 57K |
How Pixtral Large 124B (124B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 48.4 GB | Low | S87 |
Q3_K_S | 3 | 60.8 GB | Low | S87 |
NVFP4Best for your GPU | 4 | 69.4 GB | Medium | S87 |
Q4_K_M | 4 | 75.6 GB | Medium | F0 |
Q5_K_M | 5 | 89.3 GB | High | F0 |
Q6_K | 6 | 101.7 GB | High | F0 |
Q8_0 | 8 | 132.7 GB | Very High | F0 |
F16 | 16 | 254.2 GB | Maximum | F0 |
Copy-paste commands to run Pixtral Large 124B on your machine.
Run
lms load Pixtral-Large-Instruct-2411 && lms server startアップグレードオプション
NVIDIA H200 141GBコスパ重視Raises estimated decode speed by about 2317%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
NVIDIA H200 PCIe 141GBコスパ最良Raises estimated decode speed by about 2317%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
NVIDIA B200 180GBNVIDIAアップグレードRaises estimated decode speed by about 3925%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Pixtral Large 124B at Q6_K quantization (Very compromised (needs ~10.3 GB host RAM)). The recommended Q4_K_M requires 81.9 GB which exceeds available memory, but at Q6_K it needs only 121.0 GB. Expected decode speed: 2.0 tok/s.
Pixtral Large 124B (124B parameters) requires approximately 81.9 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at Q6_K using 121.0 GB.
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is Q6_K, which uses 121.0 GB.
On NVIDIA DGX Spark 128GB, Pixtral Large 124B achieves approximately 2.0 tokens per second decode speed with a time-to-first-token of 96800ms using Q6_K quantization.
For coding workloads, Pixtral Large 124B on NVIDIA DGX Spark 128GB receives a F grade with 2.0 tok/s and 4K context.
On NVIDIA DGX Spark 128GB, Pixtral Large 124B can safely use up to 4K tokens of context at Q6_K quantization. The model's official context limit is 131K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/pixtral-large-124b-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: