Pixtral Large 124B needs ~73.4 GB VRAM. AMD Instinct MI210 64GB has 64.0 GB. With Q3_K_S 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
24.3 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
6.1 tok/s
TTFT
31747 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 | 6.5 tok/s | 16226 ms | 4K |
| Coding | F | Too heavy | 6.1 tok/s | 31747 ms | 4K |
| Agentic Coding | F | Too heavy | 5.4 tok/s | 52288 ms | 4K |
| Reasoning | F | Too heavy | 6.1 tok/s | 37519 ms | 4K |
| RAG | F | Too heavy | 5.4 tok/s | 65360 ms | 4K |
How Pixtral Large 124B (124B params) fits at each quantization level on AMD Instinct MI210 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升级选项
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.
~$8,000 MSRP
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
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.
~$15,000 MSRP
Yes, AMD Instinct MI210 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: 10.4 tok/s.
Pixtral Large 124B (124B parameters) requires approximately 88.3 GB at Q4_K_M quantization. On AMD Instinct MI210 64GB, it fits at Q3_K_S using 73.4 GB.
The recommended quantization is Q4_K_M, but on AMD Instinct MI210 64GB the best fitting quantization is Q3_K_S, which uses 73.4 GB.
On AMD Instinct MI210 64GB, Pixtral Large 124B achieves approximately 10.4 tokens per second decode speed with a time-to-first-token of 18595ms using Q3_K_S quantization.
For coding workloads, Pixtral Large 124B on AMD Instinct MI210 64GB receives a F grade with 6.1 tok/s and 4K context.
On AMD Instinct MI210 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-instinct-mi210-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: