Q4_K_M
10 GBMin VRAM: 11.5 GB
Recommended VRAM: 13 GB
Min RAM: 15 GB
Context: 8K / 8K
Loading model details...
Fetching variants, compatibility details, and metadata.
Loading model details...
Fetching variants, compatibility details, and metadata.
Share GPT-OSS 20B with someone who is deciding what to run locally.
Social proof
56% of 989 scanned PCs run GPT-OSS 20B fully on GPU.
748 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
10 GBMin VRAM: 11.5 GB
Recommended VRAM: 13 GB
Min RAM: 15 GB
Context: 8K / 8K
Q5_K_M
12.5 GBMin VRAM: 14.4 GB
Recommended VRAM: 16.3 GB
Min RAM: 19 GB
Context: 8K / 8K
Q8_0
20 GBMin VRAM: 23 GB
Recommended VRAM: 26 GB
Min RAM: 30 GB
Context: 8K / 8K
FP16
40 GBMin VRAM: 46 GB
Recommended VRAM: 52 GB
Min RAM: 60 GB
Context: 8K / 8K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q4_K_M | 10 GB | 11.5 GB | 13 GB | 15 GB | 8K / 8K |
| Q5_K_M | 12.5 GB | 14.4 GB | 16.3 GB | 19 GB | 8K / 8K |
| Q8_0 | 20 GB | 23 GB | 26 GB | 30 GB | 8K / 8K |
| FP16 | 40 GB | 46 GB | 52 GB | 60 GB | 8K / 8K |
These GPUs meet the recommended 13 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 · ~76.8 tok/s
Lowest cost that meets recommended VRAM
Check price on AmazonFastest Pick
NVIDIA GeForce RTX 509032 GB VRAM · ~143.4 tok/s
Highest estimated throughput
Check price on AmazonBest Value
NVIDIA GeForce RTX 5070 Ti16 GB VRAM · ~71.7 tok/s
Best speed per dollar of VRAM
Check price on AmazonNeed a detailed comparison? See all GPU rankings for GPT-OSS 20B.