Pixtral Large 124B needs ~73.4 GB VRAM. NVIDIA A16 64GB has 64.0 GB. With Q3_K_S quantization, expect ~4 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
24.3 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
2.6 tok/s
TTFT
75557 ms
Safe context
4K
Memory
88.3 GB / 64.0 GB
Offload
30%
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.
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 7.8 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 2.7 tok/s | 38619 ms | 4K |
| Coding | F | Too heavy | 2.6 tok/s | 75557 ms | 4K |
| Agentic Coding | F | Too heavy | 2.3 tok/s | 124445 ms | 4K |
| Reasoning | F | Too heavy | 2.6 tok/s | 89294 ms | 4K |
| RAG | F | Too heavy | 2.3 tok/s | 155556 ms | 4K |
How Pixtral Large 124B (124B params) fits at each quantization level on NVIDIA A16 64GB (64.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 48.4 GB | Low | S87 |
Q3_K_S | 3 | 60.8 GB | Low | F0 |
NVFP4 | 4 | 69.4 GB | Medium | F0 |
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
RTX PRO 6000 Blackwell Workstation Edition 96GBコスパ重視Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$9,999 MSRP
RTX PRO 6000 Blackwell Server Edition 96GBコスパ最良Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$9,999 MSRP
NVIDIA H20 96GBNVIDIAアップグレードMakes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$12,000 MSRP
Yes, NVIDIA A16 64GB can run Pixtral Large 124B at Q3_K_S quantization (Very compromised (needs ~7.8 GB host RAM)). The recommended Q4_K_M requires 88.3 GB which exceeds available memory, but at Q3_K_S it needs only 73.4 GB. Expected decode speed: 4.4 tok/s.
Pixtral Large 124B (124B parameters) requires approximately 88.3 GB at Q4_K_M quantization. On NVIDIA A16 64GB, it fits at Q3_K_S using 73.4 GB.
The recommended quantization is Q4_K_M, but on NVIDIA A16 64GB the best fitting quantization is Q3_K_S, which uses 73.4 GB.
On NVIDIA A16 64GB, Pixtral Large 124B achieves approximately 4.4 tokens per second decode speed with a time-to-first-token of 44256ms using Q3_K_S quantization.
For coding workloads, Pixtral Large 124B on NVIDIA A16 64GB receives a F grade with 2.6 tok/s and 4K context.
On NVIDIA A16 64GB, Pixtral Large 124B can safely use up to 4K tokens of context at Q3_K_S 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.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/pixtral-large-124b-on-a16-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: