What hardware runs Mistral 7B?
7.2B parameters. GGUF files: Q4_K_M 4.4 GB, Q8_0 7.7 GB (GGUF repo, model card). Est. VRAM incl. ~4k context: 5.8 GB (Q4) / 9.5 GB (Q8).
Hardware that fits at Q4 (real UK prices first, then cheapest sample price)
- RTX 3060 12GB (12 GB) £352.99 REAL
- Arc B580 (12 GB) £355.83 REAL
- RX 9060 XT 16GB (16 GB) £407.99 REAL
- RX 9070 (16 GB) £616.83 REAL
- RTX 5060 Ti 16GB (16 GB) £649.98 REAL
- RTX 5070 (12 GB) £695.71 REAL
- RX 9070 XT (16 GB) £795.18 REAL
- RTX 5070 Ti (16 GB) £1079.99 REAL
- RTX 5080 (16 GB) £1359.98 REAL
- Radeon AI PRO R9700 (32 GB) £1539.98 REAL
- RTX 5090 (32 GB) £5339.99 REAL
- Arc A770 16GB (16 GB) ~$299 sample
- Tesla P40 (24 GB) ~$300 sample
- RX 7600 XT (16 GB) ~$329 sample
- RTX 4060 Ti 16GB (16 GB) ~$449 sample
- RX 7900 XT (20 GB) ~$699 sample
- RTX 4070 Ti Super (16 GB) ~$799 sample
- RTX 3090 (24 GB) ~$800 sample
- RX 7900 XTX (24 GB) ~$899 sample
- RTX 4080 Super (16 GB) ~$999 sample
- RTX 4090 (24 GB) ~$1800 sample
- Ryzen AI Max+ 395 mini-PC (128GB unified) (128 GB) ~$1999 sample
- Mac mini M4 Pro (max 64GB unified) (64 GB) ~$2199 sample
- RTX A6000 (48 GB) ~$4500 sample
- Mac Studio M3 Ultra (max 512GB unified) (512 GB) ~$9499 sample