Can the Radeon RX 9060 XT 16 GB run Mistral-Small-3.2-24B-Instruct-2506?
Yes. The Q4_K_M GGUF of Mistral-Small-3.2-24B-Instruct-2506 is 14.33 GB (source). With our 1.5 GB allowance for runtime and short-context cache it needs about 15.8 GB, leaving 0.2 GB of the card's 16 GB free. Expected speed: ~17 tok/s estimate. Lowest tracked price: low $620, avg $812 (new) source, 2026-10-16, which works out to $36 per tok/s (#8 of 12 priced GPUs that fit this model).
Last updated Oct 16, 2026. Speed is a bandwidth-based estimate (322.3 GB/s, TechPowerUp), not a benchmark. Long contexts need more memory than our allowance.
Tight fit: under 3 GB spare means long prompts or a bigger context window may not fit. Consider a smaller quant or a card with more VRAM.
Next size up: gemma-3-27b-it (16.55 GB at Q4_K_M) needs ~18.1 GB and does not fit on one AMD Radeon RX 9060 XT 16 GB. See what runs gemma-3-27b-it.
Every priced GPU that runs Mistral-Small-3.2-24B-Instruct-2506, by cost per token/sec
| GPU | VRAM | Speed estimate | Low price | $ per tok/s |
|---|---|---|---|---|
| AMD Radeon RX 9070 | 16 GB | ~34 tok/s | $570 (new) | $17 |
| AMD Radeon RX 7800 XT | 16 GB | ~33 tok/s | $599 (new) | $18 |
| NVIDIA GeForce RTX 5070 Ti | 16 GB | ~48 tok/s | $1,120 (new) | $23 |
| AMD Radeon RX 9070 XT | 16 GB | ~34 tok/s | $810 (new) | $24 |
| AMD Radeon RX 7900 XTX | 24 GB | ~51 tok/s | $1,350 (new) | $26 |
| NVIDIA GeForce RTX 5080 | 16 GB | ~51 tok/s | $1,600 (new) | $31 |
| NVIDIA GeForce RTX 5060 Ti 16 GB | 16 GB | ~24 tok/s | $780 (new) | $33 |
| AMD Radeon RX 9060 XT 16 GB | 16 GB | ~17 tok/s | $620 (new) | $36 |
| NVIDIA GeForce RTX 3090 | 24 GB | ~50 tok/s | $1,889 (used) | $38 |
| NVIDIA GeForce RTX 4090 | 24 GB | ~54 tok/s | $3,200 (used) | $59 |
| NVIDIA GeForce RTX 5090 | 32 GB | ~95 tok/s | $6,500 (new) | $68 |
| NVIDIA RTX A6000 | 48 GB | ~41 tok/s | $6,170 (new) | $150 |
Prices: picksbycard read of Newegg listings, 2026-10-16. Prices move daily.
Buy on Amazon As an Amazon Associate I earn from qualifying purchases.