Pixtral Large 124B needs ~109.6 GB VRAM. Mac Studio M3 Ultra 256GB has 184.3 GB. With Q4_K_M quantization, expect ~7 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
8.0 tok/s
TTFT
24179 ms
Safe context
131K
Memory
109.6 GB / 184.3 GB
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
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.
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs well | 8.0 tok/s | 13188 ms | 131K |
| Coding | S | Runs well | 7.4 tok/s | 26294 ms | 131K |
| Agentic Coding | S | Runs well | 8.0 tok/s | 35169 ms | 131K |
| Reasoning | S | Runs well | 8.0 tok/s | 28575 ms | 131K |
| RAG | S | Runs well | 8.0 tok/s | 43961 ms | 131K |
Inference speed
Estimated decode speed (tokens/sec) for Pixtral Large 124B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is MacBook Pro M4 Max 128GB at ~8 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 8.0 | Offloads |
How Pixtral Large 124B (124B params) fits at each quantization level on Mac Studio M3 Ultra 256GB (184.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 48.4 GB | Low | A81 |
Q3_K_S | 3 | 60.8 GB | Low | A83 |
NVFP4 | 4 |
Copy-paste commands to run Pixtral Large 124B on your machine.
Run
lms load Pixtral-Large-Instruct-2411 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 DeepSeek V4 Flash | 284B | S | 17.8 tok/s |
Yes, Mac Studio M3 Ultra 256GB can run Pixtral Large 124B with a S grade (Runs well). Expected decode speed: 7.4 tok/s.
Pixtral Large 124B (124B parameters) requires approximately 109.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Pixtral Large 124B is Q4_K_M, which balances quality and memory efficiency.
On Mac Studio M3 Ultra 256GB, Pixtral Large 124B achieves approximately 7.4 tokens per second decode speed with a time-to-first-token of 26294ms using Q4_K_M quantization.
For coding workloads, Pixtral Large 124B on Mac Studio M3 Ultra 256GB receives a S grade with 7.4 tok/s and 131K context.
On Mac Studio M3 Ultra 256GB, Pixtral Large 124B can safely use up to 131K tokens of context. 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-large-124b-on-m3-ultra-256gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| 256 GB |
| Q4_K_M |
| 8.0 |
| Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 6.2 | Offloads |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 5.9 | Offloads |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 3.9 | Too big |
2× RX 7900 XTX 24GB | 48 GB | Q4_K_M | 3.6 | Too big |
 2× RTX 4090 24GB | 48 GB | Q4_K_M | 2.6 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 2.4 | Too big |
| 2× RTX 3090 24GB | 48 GB | Q4_K_M | 2.2 | Too big |
| RTX 5090 32GB | 32 GB | Q4_K_M | 2.0 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 2.0 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 2.0 | Too big |
| 4× RTX 3060 12GB | 48 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
69.4 GB |
| Medium |
| A84 |
Q4_K_M | 4 | 75.6 GB | Medium | A84 |
Q5_K_M | 5 | 89.3 GB | High | S86 |
Q6_K | 6 | 101.7 GB | High | S87 |
Q8_0Best for your GPU | 8 | 132.7 GB | Very High | S87 |
F16 | 16 | 254.2 GB | Maximum | F0 |
Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Not always. Mac Studio M3 Ultra 256GB 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.