// RUN ON CONSUMER GPU

Run GLM-4-9B-0414 on Consumer GPU hardware

32 options ranked by estimated speed at Q4 / 8k context.

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~309.3 yes 175k ~$1,999
NVIDIA GeForce RTX 4090 → ~174 yes 119k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~174 yes 119k ~$1,999
NVIDIA GeForce RTX 5080 → ~165.7 yes 62k ~$999
NVIDIA GeForce RTX 3090 → ~161.6 yes 119k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~157.4 yes 34k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~154.7 yes 62k ~$749
AMD Radeon RX 7900 XTX → ~146.7 yes 119k ~$999
NVIDIA GeForce RTX 3080 10GB → ~131.2 yes 20k ~$699
NVIDIA GeForce RTX 4080 → ~127 yes 62k ~$1,199
AMD Radeon RX 7900 XT → ~122.2 yes 90k ~$899
NVIDIA GeForce RTX 5070 → ~116 yes 34k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~116 yes 62k ~$799
NVIDIA GeForce RTX 3070 Ti → ~105 tight 6k ~$599
AMD Radeon RX 9070 XT → ~98.4 yes 62k ~$599
AMD Radeon RX 7800 XT → ~95.3 yes 62k ~$499
NVIDIA GeForce RTX 4070 Super → ~87 yes 34k ~$599
NVIDIA GeForce RTX 4070 → ~87 yes 34k ~$599
Intel Arc Pro B70 → ~86.9 yes 175k —
Intel Arc A770 16GB → ~80 yes 62k ~$329
AMD Radeon RX 6800 XT → ~78.2 yes 62k ~$649
AMD Radeon RX 6900 XT → ~78.2 yes 62k ~$999
NVIDIA GeForce RTX 3070 → ~77.3 tight 6k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~77.3 yes 62k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~77.3 tight 6k ~$379
Intel Arc Pro B60 → ~65.1 yes 119k —
Intel Arc B580 12GB → ~65.1 yes 34k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~49.7 tight 6k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~49.7 yes 62k ~$499
NVIDIA DGX Spark → ~47.1 yes 829k ~$3,999
AMD Ryzen AI Max+ 395 → ~39.1 yes 829k ~$1,999
Intel Arc Pro B50 → ~32 yes 62k —

Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.

→ GLM-4-9B-0414 overview → All hardware

FAQ

What Consumer GPU hardware runs GLM-4-9B-0414?▶

On GenAIList, 32 Consumer GPU options can run GLM-4-9B-0414 at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~309.3 tok/s.

How fast is GLM-4-9B-0414 on Consumer GPU hardware?▶

Estimated generation speed ranges from ~32 to ~309.3 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.