RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can glm 4 9b run on the RX 7900 XTX?

Yes. At 8K context the best fit is Q8_0, using about 15.0 GB of the 22.8 GB usable on the RX 7900 XTX. Estimated speed ceiling: ~96 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •6.9 GB Fits9.4 GB Fits240
3-bit (Q3_K_M) •7.9 GB Fits10.4 GB Fits190
4-bit (Q4_K_M) •9.0 GB Fits11.5 GB Fits154
5-bit (Q5_K_M) •9.8 GB Fits12.3 GB Fits134
6-bit (Q6_K) •10.9 GB Fits13.4 GB Fits116
8-bit (Q8_0) •12.5 GB Fits15.0 GB Fits96
16-bit (F16/BF16) •20.7 GB Tight23.2 GB No—

• real GGUF file size from mradermacher/glm-4-9b-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.

More

glm 4 9b on every GPU and Mac · Every model that runs on the RX 7900 XTX · Other models that fit 24 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (zai-org/glm-4-9b), AMD specs. Data as of 2026-11-17.