← CanIRunLocal · All hardware · All models
Yes, with partial offload (slower). GLM-4.7-Flash 30B-A3B (MoE) on RTX 4080 16GB at Q4_K_M uses system RAM (20.4 GB needed, 15.5 GB usable), about 35 tok/s (estimate).
Hardware: RTX 4080 16GB · Model: GLM-4.7-Flash 30B-A3B (MoE)
RTX 4080 16GB has 16 GB of VRAM and 717 GB/s of memory bandwidth. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 15.5 GB. Partial offload may also use 60% of that system RAM. GLM-4.7-Flash 30B-A3B (MoE) (31.2B, 3B active, Z.ai) at Q4_K_M is a 19 GB download and needs 20.4 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 19 GB |
| Memory needed | 20.4 GB |
| Usable fast memory | 15.5 GB |
| Fit | partial offload (slower) |
| Estimated speed | ~35 tok/s (estimate) |
| Command | ollama run glm-4.7-flash:latest |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt