GPUs / Intel
UHD Graphics
- Memory
- DDR4 / DDR5
- Bus
- 128-bit
- Published peak
- 51.2 to 102.4 GB/s
- Capacity
- from 8 GB
Measured
- Read
- 32.3GB/s
- Write
- 12.7GB/s
- Copy
- 22.3GB/s
- Random
- 1.28GB/s
- Latency
- 643ns
- Sustain
- 22.2GB/s
Medians of 5 verified runs from 3 operators.
Local AI speed
| Model | Parameters | 4-bit, tokens/s | 8-bit, tokens/s |
|---|---|---|---|
| Llama 3.1 8B | 8.03B | ≤ 8.0 | Does not fit |
| Qwen 2.5 14B | 14.7B | ≤ 4.4 | Does not fit |
| gpt-oss-20b | 21B, 3.6B active | Does not fit | Does not fit |
| Mistral Small 24B | 24B | Does not fit | Does not fit |
| Qwen 2.5 32B | 32.5B | Does not fit | Does not fit |
| Llama 3.3 70B | 70.6B | Does not fit | Does not fit |
| gpt-oss-120b | 117B, 5.1B active | Does not fit | Does not fit |