Can glm 4 9b run on the RTX 3080 10GB?
Yes. At 8K context the best fit is Q2_K, using about 9.4 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~190 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) • | 6.9 GB Fits | 9.4 GB Tight | 190 |
| 3-bit (Q3_K_M) • | 7.9 GB Fits | 10.4 GB No | — |
| 4-bit (Q4_K_M) • | 9.0 GB Tight | 11.5 GB No | — |
| 5-bit (Q5_K_M) • | 9.8 GB No | 12.3 GB No | — |
| 6-bit (Q6_K) • | 10.9 GB No | 13.4 GB No | — |
| 8-bit (Q8_0) • | 12.5 GB No | 15.0 GB No | — |
| 16-bit (F16/BF16) • | 20.7 GB No | 23.2 GB No | — |
• real GGUF file size from mradermacher/glm-4-9b-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.
More
glm 4 9b on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (zai-org/glm-4-9b), NVIDIA specs. Data as of 2026-11-17.