Q4_K_M
61.5 GBMin VRAM: 70.7 GB
Recommended VRAM: 80 GB
Min RAM: 93 GB
Context: 8K / 8K
Loading model details...
Fetching variants, compatibility details, and metadata.
Loading model details...
Fetching variants, compatibility details, and metadata.
Share Devstral 2 123B with someone who is deciding what to run locally.
Social proof
6% of 981 scanned PCs run Devstral 2 123B fully on GPU.
285 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
61.5 GBMin VRAM: 70.7 GB
Recommended VRAM: 80 GB
Min RAM: 93 GB
Context: 8K / 8K
Q5_K_M
76.9 GBMin VRAM: 88.4 GB
Recommended VRAM: 100 GB
Min RAM: 116 GB
Context: 8K / 8K
Q8_0
123 GBMin VRAM: 141.5 GB
Recommended VRAM: 159.9 GB
Min RAM: 185 GB
Context: 8K / 8K
FP16
246 GBMin VRAM: 282.9 GB
Recommended VRAM: 319.8 GB
Min RAM: 369 GB
Context: 8K / 8K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q4_K_M | 61.5 GB | 70.7 GB | 80 GB | 93 GB | 8K / 8K |
| Q5_K_M | 76.9 GB | 88.4 GB | 100 GB | 116 GB | 8K / 8K |
| Q8_0 | 123 GB | 141.5 GB | 159.9 GB | 185 GB | 8K / 8K |
| FP16 | 246 GB | 282.9 GB | 319.8 GB | 369 GB | 8K / 8K |
These GPUs meet the recommended 80 GB VRAM for the Q4_K_M quantization. Estimated speeds are approximate and assume full GPU offloading.
Budget Pick
Apple M2 Max96 GB VRAM · ~5.2 tok/s
Lowest cost that meets recommended VRAM
Check price on AmazonFastest Pick
Apple M4 Ultra256 GB VRAM · ~14.2 tok/s
Highest estimated throughput
Check price on AmazonBest Value
Apple M1 Ultra128 GB VRAM · ~10.4 tok/s
Best speed per dollar of VRAM
Check price on AmazonNeed a detailed comparison? See all GPU rankings for Devstral 2 123B.