gpt-oss · Aug 2025 · 21B total, 3.6B active
gpt-oss-20b: what runs it and what it costs today
At Q4_K_M with 8K of context it needs about 15 GB of memory. The cheapest machine that runs it today is the NVIDIA Tesla P100 16GB at $127.63.
By quantization
Memory needed includes the KV cache for 8K of context and runtime overhead. The cheapest machine is the lowest live price, item plus shipping, that fits with room for that context.
| Quant | Needs | Cheapest machine that fits today | Price |
|---|---|---|---|
| FP16 | 44 GB | Framework Desktop, Ryzen AI Max+ 395, 128 GB | $3,464.65 |
| Q8_0 | 24 GB | AMD Radeon Instinct MI50 32GB | $600 |
| Q6_K | 19 GB | NVIDIA Tesla P40 | $273 |
| Q5_K_M | 17 GB | NVIDIA Tesla P40 | $273 |
| Q4_K_M | 15 GB | NVIDIA Tesla P100 16GB | $127.63 |
| Q3_K_M | 12 GB | NVIDIA Tesla P100 16GB | $127.63 |
| IQ2_M | 9 GB | NVIDIA Tesla P100 16GB | $127.63 |
Every machine at Q4_K_M 33 fit
| Machine | Memory | Fit at 8K | Est. speed | Price | Per GB |
|---|---|---|---|---|---|
| NVIDIA Tesla P100 16GB card | 16 GB | fits 33K ctx | ~220 tok/s | $127.63 eBay | $7/GB |
| AMD Radeon Instinct MI50 16GB card | 16 GB | fits 33K ctx | ~230 tok/s | $228.78 eBay | $14/GB |
| NVIDIA Tesla P40 card | 24 GB | fits 128K+ ctx | ~100 tok/s | $273 eBay | $11/GB |
| AMD Radeon Instinct MI50 32GB card | 32 GB | fits 128K+ ctx | ~230 tok/s | $600 eBay | $18/GB |
| NVIDIA GeForce RTX 5060 Ti 16GB card | 16 GB | fits 33K ctx | ~130 tok/s | $617.99 eBay | $38/GB |
| NVIDIA GeForce RTX 4060 Ti 16GB card | 16 GB | fits 33K ctx | ~85 tok/s | $656.27 eBay | $41/GB |
| AMD Radeon RX 7900 XTX card | 24 GB | fits 128K+ ctx | ~220 tok/s | $900 eBay | $37/GB |
| NVIDIA RTX A4000 card | 16 GB | fits 33K ctx | ~130 tok/s | $1,079.94 eBay | $67/GB |
| NVIDIA GeForce RTX 3090 card | 24 GB | fits 128K+ ctx | ~280 tok/s | $1,497 eBay | $62/GB |
| NVIDIA RTX 4000 SFF Ada card | 20 GB | fits 113K ctx | ~83 tok/s | $1,510.30 eBay | $75/GB |
| AMD Radeon AI PRO R9700 card | 32 GB | fits 128K+ ctx | ~150 tok/s | $1,820 eBay | $56/GB |
| NVIDIA GeForce RTX 4090 card | 24 GB | fits 128K+ ctx | ~300 tok/s | $2,083.48 eBay | $86/GB |
| NVIDIA RTX A5000 card | 24 GB | fits 128K+ ctx | ~230 tok/s | $2,325.65 eBay | $96/GB |
| NVIDIA RTX PRO 4000 Blackwell card | 24 GB | fits 128K+ ctx | ~200 tok/s | $2,827.16 eBay | $117/GB |
| NVIDIA RTX PRO 4000 Blackwell SFF card | 24 GB | fits 128K+ ctx | ~130 tok/s | $2,899 eBay | $120/GB |
| Framework Desktop, Ryzen AI Max+ 395, 128 GB desktop box | 128 GB | fits 128K+ ctx | ~58 tok/s | $3,464.65 eBay | $27/GB |
| GMKtec EVO-X2, Ryzen AI Max+ 395, 128 GB desktop box | 128 GB | fits 128K+ ctx | ~58 tok/s | $3,649.99 eBay | $28/GB |
| NVIDIA RTX PRO 4500 Blackwell card | 32 GB | fits 128K+ ctx | ~270 tok/s | $4,450 eBay | $139/GB |
| NVIDIA RTX A6000 card | 48 GB | fits 128K+ ctx | ~230 tok/s | $4,500 eBay | $93/GB |
| Apple Mac Studio M4 Max, 128 GB desktop box | 128 GB | fits 128K+ ctx | ~150 tok/s | $4,899 eBay | $38/GB |
| NVIDIA GeForce RTX 5090 card | 32 GB | fits 128K+ ctx | ~530 tok/s | $4,920.99 eBay | $153/GB |
| ASUS Ascent GX10 desktop box | 128 GB | fits 128K+ ctx | ~81 tok/s | $6,099.99 eBay | $47/GB |
| Acer Veriton GN100 desktop box | 128 GB | fits 128K+ ctx | ~81 tok/s | $6,367.19 eBay | $49/GB |
| HP ZGX Nano AI Station desktop box | 128 GB | fits 128K+ ctx | ~81 tok/s | $6,440.40 eBay | $50/GB |
| Gigabyte AI TOP ATOM desktop box | 128 GB | fits 128K+ ctx | ~81 tok/s | $6,999 eBay | $54/GB |
| NVIDIA RTX PRO 5000 Blackwell card | 48 GB | fits 128K+ ctx | ~400 tok/s | $7,099.99 eBay | $147/GB |
| NVIDIA RTX 6000 Ada card | 48 GB | fits 128K+ ctx | ~280 tok/s | $7,698.43 eBay | $160/GB |
| NVIDIA DGX Spark desktop box | 128 GB | fits 128K+ ctx | ~81 tok/s | $7,799.98 eBay | $60/GB |
| Apple Mac Studio M3 Ultra, 256 GB desktop box | 256 GB | fits 128K+ ctx | ~220 tok/s | $8,499 eBay | $33/GB |
| NVIDIA A100 80GB PCIe card | 80 GB | fits 128K+ ctx | ~570 tok/s | $15,299 eBay | $191/GB |
| NVIDIA RTX PRO 6000 Blackwell card | 96 GB | fits 128K+ ctx | ~530 tok/s | $16,499 eBay | $171/GB |
| Apple Mac Studio M3 Ultra, 512 GB desktop box | 512 GB | fits 128K+ ctx | ~220 tok/s | $18,566.48 eBay | $36/GB |
| NVIDIA H100 80GB PCIe card | 80 GB | fits 128K+ ctx | ~590 tok/s | $26,995.21 eBay | $337/GB |
| NVIDIA GeForce RTX 3060 12GB card | 12 GB | does not fit | $320 eBay | $26/GB |
Estimates assume the whole model in memory with llama.cpp-style inference; see how we estimate. Prices are the cheapest live eBay listing that passed our filters, item plus shipping.