Home / Models / GPT-OSS 20B / NVIDIA RTX 3050 6 GB
Can GPT-OSS 20B run on NVIDIA RTX 3050 6 GB?
Can it run? Yes, with CPU/RAM offload. Full GPU fit? No.
Can it run?
- Can it run?
- Yes, with CPU/RAM offload. This is not equivalent to full-GPU inference.
- Full GPU fit?
- No
- Model
- GPT-OSS 20B · 22B
- GPU
- NVIDIA RTX 3050 6 GB · 6 GB advertised
What else can NVIDIA RTX 3050 6 GB run? · Find other GPUs for GPT-OSS 20B · See 2× multi-GPU options
Memory calculation
Breakdown for Q4 at 8K context, batch size 1. Calculator v1.0.0.
| Model weights | 12.6 GB |
|---|---|
| KV cache | 0.4 GB |
| Runtime reserve | 1.1 GB |
| Safety margin | 0.6 GB |
| Required (estimated) | 14.7 GB |
| GPU usable VRAM | 5.4 GB |
Result: CPU RAM OFFLOAD REQUIRED
Quantization table
| Quantization | 2K | 4K | 8K | 16K | 32K | 64K | 128K |
|---|---|---|---|---|---|---|---|
| BF16 | No | No | No | No | No | No | No |
| FP16 | No | No | No | No | No | No | No |
| Q3 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q4 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q5 | No | No | No | No | No | No | No |
| Q6 | No | No | No | No | No | No | No |
| Q8 | No | No | No | No | No | No | No |
What fits entirely in VRAM?
No calculated full-VRAM fit at the evaluated quantizations and context lengths.
What requires RAM offload?
Weights may run with CPU/RAM offload. That is not equivalent to full-GPU inference. Performance numbers below are only published for full-VRAM fits.
Performance
No llama.cpp performance result is published for this pair yet. Memory fit above is unchanged. How performance is calculated
Available graphics cards
These SKUs use this GPU chip. Amazon CTAs appear only for EXACT/HIGH matches. Absence of a price does not change the compatibility result above.
ASUS Dual -RTX3050-O6G NVIDIA GeForce RTX 3050 6 GB GDDR6
6 GB · Amazon EXACT
Check price on Amazon
MSI GEFORCE RTX 3050 LP 6G OC graphics card NVIDIA 6 GB GDDR6
6 GB · Amazon EXACT
Check price on Amazon
GIGABYTE GeForce RTX 3050 OC Low Profile 6G NVIDIA 6 GB GDDR6
6 GB · Amazon EXACT
Check price on Amazon
Sources
Model: official config openai/gpt-oss-20b (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 8K: DOES_NOT_FIT. Amazon: affiliate commerce match, not a spec source.