BuildsGPUsModelsGuidesMethodologyNewsletter

What GPU do you need to run Mistral-7B-Instruct-v0.3?

7.25B parameters (Hugging Face, accessed 2026-10-15). Q4_K_M GGUF: 4.37 GB (source).

Single GPU that fitsVRAMSpeed estimatePrice
NVIDIA GeForce RTX 5060 Ti 8 GB8 GB~78 tok/slow $450, avg $809 (new) source, 2026-10-16
NVIDIA GeForce RTX 50608 GB~78 tok/slow $410, avg $550 (new) source, 2026-10-16
NVIDIA GeForce RTX 40608 GB~47 tok/scheck price
NVIDIA GeForce RTX 308010 GB~132 tok/scheck price
NVIDIA GeForce RTX 507012 GB~117 tok/slow $800, avg $1,086 (new) source, 2026-10-16
NVIDIA GeForce RTX 4070 SUPER12 GB~88 tok/slow $966, avg $1,156 (used) source, 2026-10-16
NVIDIA GeForce RTX 407012 GB~88 tok/scheck price
NVIDIA GeForce RTX 3080 Ti12 GB~159 tok/scheck price
NVIDIA GeForce RTX 3060 12 GB12 GB~63 tok/slow $455, avg $588 (used) source, 2026-10-16
Intel Arc B58012 GB~79 tok/slow $330, avg $446 (new) source, 2026-10-16
NVIDIA GeForce RTX 508016 GB~167 tok/slow $1,600, avg $2,399 (new) source, 2026-10-16
NVIDIA GeForce RTX 5070 Ti16 GB~156 tok/slow $1,120, avg $1,792 (new) source, 2026-10-16
NVIDIA GeForce RTX 5060 Ti 16 GB16 GB~78 tok/slow $780, avg $1,146 (new) source, 2026-10-16
NVIDIA GeForce RTX 4080 SUPER16 GB~128 tok/scheck price
NVIDIA GeForce RTX 408016 GB~125 tok/scheck price
NVIDIA GeForce RTX 4070 Ti SUPER16 GB~117 tok/scheck price
NVIDIA GeForce RTX 4060 Ti 16 GB16 GB~50 tok/scheck price
AMD Radeon RX 9070 XT16 GB~112 tok/slow $810, avg $1,194 (new) source, 2026-10-16
AMD Radeon RX 907016 GB~112 tok/slow $570, avg $1,052 (new) source, 2026-10-16
AMD Radeon RX 9060 XT 16 GB16 GB~56 tok/slow $620, avg $812 (new) source, 2026-10-16
AMD Radeon RX 7800 XT16 GB~109 tok/slow $599, avg $834 (new) source, 2026-10-16
AMD Radeon RX 7600 XT16 GB~50 tok/scheck price
AMD Radeon RX 7900 XT20 GB~139 tok/scheck price
NVIDIA GeForce RTX 409024 GB~176 tok/slow $3,200, avg $4,663 (used) source, 2026-10-16
NVIDIA GeForce RTX 3090 Ti24 GB~176 tok/scheck price
NVIDIA GeForce RTX 309024 GB~163 tok/slow $1,889, avg $2,404 (used) source, 2026-10-16
AMD Radeon RX 7900 XTX24 GB~167 tok/slow $1,350, avg $1,552 (new) source, 2026-10-16
NVIDIA Tesla P4024 GB~60 tok/scheck price
NVIDIA GeForce RTX 509032 GB~311 tok/slow $6,500, avg $8,757 (new) source, 2026-10-16
AMD Radeon AI PRO R970032 GB~112 tok/scheck price
Apple Mac Studio M5 Max (32-core GPU, 36 GB)36 GB~80 tok/slow $2,499 (new) source, 2026-10-16
NVIDIA RTX A600048 GB~134 tok/slow $6,170 (new) source, 2026-10-16
NVIDIA RTX 6000 Ada Generation48 GB~167 tok/scheck price
Apple Mac Studio M5 Max (40-core GPU, 64 GB)64 GB~107 tok/scheck price
Apple Mac Studio M5 Ultra (64-core GPU, 96 GB)96 GB~209 tok/scheck price
Framework Desktop, AMD Ryzen AI Max+ PRO 495 (Strix Halo), 192 GB192 GB~47 tok/slow $6,799 (new) source, 2026-10-16

Speed calculator estimate

Estimate = 0.76 × bandwidth ÷ GB read per token (Q4 file size, scaled by active/total parameters for MoE). Fit = file size + 1.5 GB headroom ≤ total VRAM. Multi-GPU: VRAM adds, speed uses one card's bandwidth (layer split). Short context only. How this works

Related