← CanIRunLocal · All hardware · All models
Yes. GLM-OCR 0.9B fits in fast memory on DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) at BF16 (3.7 GB needed, 108.8 GB usable), about 76 tok/s (estimate).
Hardware: DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) · Model: GLM-OCR 0.9B
DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) has 128 GB of unified memory and 273 GB/s of memory bandwidth. DGX OS keeps about 15% of unified memory, so Ollama can use 108.8 GB. GLM-OCR 0.9B (1.33B, Z.ai) at BF16 is a 2.7 GB download and needs 3.7 GB with headroom for about 8k tokens.
| Best quant | BF16 |
|---|---|
| Download size | 2.7 GB |
| Memory needed | 3.7 GB |
| Usable fast memory | 108.8 GB |
| Fit | fits in fast memory |
| Estimated speed | ~76 tok/s (estimate) |
| Command | ollama run glm-ocr: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