🔌
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 Huawei Ascend 950DT run OmniFusion-7B (InternViT-6B-448px V1-2)?
Yes — here's how fast and up to what context, with real measured numbers.
OmniFusion-7B (InternViT-6B-448px V1-2) on the Huawei Ascend 950DT
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 646k | 103.7-126 t/s | ~1-1.3 (slow) |
| Q8 | yes | 723k | 207.3-252 t/s | ~2.1-2.5 (slow) |
| Q4 | yes | 757k | 370.2-450 t/s | ~3.7-4.5 (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.
→ All models on the Huawei Ascend 950DT
→ OmniFusion-7B (InternViT-6B-448px V1-2) specs
→ Other hardware
FAQ
Can the Huawei Ascend 950DT run OmniFusion-7B (InternViT-6B-448px V1-2)?▶
Yes. At Q4 it generates ~370.2-450 tok/s and fits up to 757k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.7-4.5 tok/s.
How much context fits?▶
At Q4, up to about 757k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.