Q4_K_M
12.6 GBMin VRAM: 14 GB
Recommended VRAM: 16 GB
Min RAM: 20 GB
Context: 8K / 128K
Loading model details...
Fetching variants, compatibility details, and metadata.
Loading model details...
Fetching variants, compatibility details, and metadata.
Model Detail
Share Mistral Small 3.1 24B with someone who is deciding what to run locally.
Social proof
56% of 984 scanned PCs run Mistral Small 3.1 24B fully on GPU.
683 keep at least some work on GPU. Based on anonymous compatibility checks.
General-purpose local model brief
Best for
Consider alternatives if
Quantization tip: Benchmark at least two quantizations and validate with a task-specific eval set before production use.
New to local models? Smaller quantization variants are easier to run, while larger ones can improve quality at the cost of more memory.
Q4_K_M
12.6 GBMin VRAM: 14 GB
Recommended VRAM: 16 GB
Min RAM: 20 GB
Context: 8K / 128K
FP16
45.6 GBMin VRAM: 48 GB
Recommended VRAM: 54 GB
Min RAM: 60 GB
Context: 8K / 128K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q4_K_M | 12.6 GB | 14 GB | 16 GB | 20 GB | 8K / 128K |
| FP16 | 45.6 GB | 48 GB | 54 GB | 60 GB | 8K / 128K |
These GPUs meet the recommended 16 GB VRAM for the Q4_K_M quantization. Estimated speeds are approximate and assume full GPU offloading.
Budget Pick
NVIDIA GeForce RTX 508016 GB VRAM · ~61 tok/s
Lowest cost that meets recommended VRAM
Check price on AmazonFastest Pick
NVIDIA GeForce RTX 509032 GB VRAM · ~113.8 tok/s
Highest estimated throughput
Check price on AmazonBest Value
NVIDIA GeForce RTX 5070 Ti16 GB VRAM · ~56.9 tok/s
Best speed per dollar of VRAM
Check price on AmazonNeed a detailed comparison? See all GPU rankings for Mistral Small 3.1 24B.