🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Intel Gaudi 3 run GLM-10B-bidirectional?
Yes — here's how fast and up to what context, with real measured numbers.
GLM-10B-bidirectional on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 588k | 107.3-133.2 t/s | ~1.2-1.4 (slow) |
| Q8 | yes | 649k | 214.6-266.4 t/s | ~2.3-2.9 (slow) |
| Q4 | yes | 675k | 383.2-475.7 t/s | ~4.1-5.1 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the Intel Gaudi 3 run GLM-10B-bidirectional?▶
Yes. At Q4 it generates ~383.2-475.7 tok/s and fits up to 675k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.1-5.1 tok/s.
How much context fits?▶
At Q4, up to about 675k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.