RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GLM Z1 32B 0414 run on the RX 7900 XT?

Yes. At 8K context the best fit is Q3_K_M, using about 16.0 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~50 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •12.4 GB Fits12.6 GB Fits14.0 GB Fits65
3-bit (Q3_K_M) •15.7 GB Fits16.0 GB Fits17.4 GB Tight50
4-bit (Q4_K_M) •19.3 GB No19.5 GB No20.9 GB No—
5-bit (Q5_K_M) •22.4 GB No22.7 GB No24.1 GB No—
6-bit (Q6_K) •25.8 GB No26.1 GB No27.5 GB No—
8-bit (Q8_0) •33.2 GB No33.4 GB No34.8 GB No—
16-bit (F16/BF16) •61.6 GB No61.8 GB No63.3 GB No—

• real GGUF file size from unsloth/GLM-Z1-32B-0414-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.

More

GLM Z1 32B 0414 on every GPU and Mac · Every model that runs on the RX 7900 XT · Other models that fit 24 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (zai-org/GLM-Z1-32B-0414), AMD specs. Data as of 2026-11-17.