Mistral Small 3.2 24B Instruct 2506 needs ~37.6 GB VRAM. AMD Instinct MI300X 192GB has 192.0 GB. With Q4_K_M quantization, expect ~282 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
282.4 tok/s
TTFT
686 ms
Safe context
895K
Memory
37.6 GB / 192.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 282.4 tok/s | 374 ms | 895K |
| Coding | C | Runs well | 282.4 tok/s | 686 ms | 895K |
| Agentic Coding | C | Runs well | 282.4 tok/s | 997 ms | 895K |
| Reasoning | C | Runs well | 282.4 tok/s | 810 ms | 895K |
| RAG | C | Runs well | 282.4 tok/s | 1247 ms | 895K |
Inference speed
Estimated decode speed (tokens/sec) for Mistral Small 3.2 24B Instruct 2506 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~82 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? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 82.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 52.3 | Tight |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 47.2 | Tight |
| RTX 3090 24GB | 24 GB | Q4_K_M | 44.8 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 38.0 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 34.2 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 34.2 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 31.7 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 30.1 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 19.1 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 16.4 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 15.0 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 6.7 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 4.2 | Too big |
| RTX 4060 8GB | 8 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.
How Mistral Small 3.2 24B Instruct 2506 (24B params) fits at each quantization level on AMD Instinct MI300X 192GB (192.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | D37 |
Q3_K_S | 3 | 11.8 GB | Low | D37 |
NVFP4 | 4 | 13.4 GB | Medium | D37 |
Q4_K_M | 4 | 14.6 GB | Medium | D37 |
Q5_K_M | 5 | 17.3 GB | High | D37 |
Q6_K | 6 | 19.7 GB | High | D38 |
Q8_0 | 8 | 25.7 GB | Very High | D38 |
F16Best for your GPU | 16 | 49.2 GB | Maximum | C41 |
Copy-paste commands to run Mistral Small 3.2 24B Instruct 2506 on your machine.
Run
lms load hf-unsloth--mistral-small-3-2-24b-instruct-2506-gguf && lms server startYes, AMD Instinct MI300X 192GB can run Mistral Small 3.2 24B Instruct 2506 with a C grade (Runs well). Expected decode speed: 282.4 tok/s.
Mistral Small 3.2 24B Instruct 2506 (24B parameters) requires approximately 37.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Mistral Small 3.2 24B Instruct 2506 is Q4_K_M, which balances quality and memory efficiency.
On AMD Instinct MI300X 192GB, Mistral Small 3.2 24B Instruct 2506 achieves approximately 282.4 tokens per second decode speed with a time-to-first-token of 686ms using Q4_K_M quantization.
For coding workloads, Mistral Small 3.2 24B Instruct 2506 on AMD Instinct MI300X 192GB receives a C grade with 282.4 tok/s and 895K context.
On AMD Instinct MI300X 192GB, Mistral Small 3.2 24B Instruct 2506 can safely use up to 895K tokens of context. The model's official context limit is —, 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/hf-unsloth--mistral-small-3-2-24b-instruct-2506-gguf-on-instinct-mi300x-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: