Update README.md
Browse files
README.md
CHANGED
|
@@ -316,12 +316,6 @@ CompactifAI was applied to produce a smaller, efficient model (16B parameters) w
|
|
| 316 |
- **Measure Window:** Each phase lasts 3 minutes (excluding ramp-up and cool-down periods).
|
| 317 |
- **Workload shape:** 8k/16k workload as in the original model's card.
|
| 318 |
|
| 319 |
-
| Model | System throughput (tok/s, p50) | TTFT (s, p50) | Model weights (GB) |
|
| 320 |
-
| :--- | ---: | ---: | ---: |
|
| 321 |
-
| Nemotron 3 Nano 30B A3B | 3,363 | 2.18 | 59 |
|
| 322 |
-
| Pulsar 16B (BF16) | 3,760 | 1.80 | 30 |
|
| 323 |
-
| Pulsar 16B (fp8) | 4,808 | 1.24 | 16 |
|
| 324 |
-
| Pulsar 16B (nvfp4) | 4,735 | 1.25 | 10 |
|
| 325 |
|
| 326 |
### Long Context
|
| 327 |
Pulsar 16B preserves strong long-context behavior after compression, tracking the Nemotron-3-Nano-30B-A3B baseline closely across retrieval-heavy and full-suite long-context evaluations. Results are reported for LongBench v1, AA-LCR, NIAH, and RULER groupings up to 256k context.
|
|
|
|
| 316 |
- **Measure Window:** Each phase lasts 3 minutes (excluding ramp-up and cool-down periods).
|
| 317 |
- **Workload shape:** 8k/16k workload as in the original model's card.
|
| 318 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 319 |
|
| 320 |
### Long Context
|
| 321 |
Pulsar 16B preserves strong long-context behavior after compression, tracking the Nemotron-3-Nano-30B-A3B baseline closely across retrieval-heavy and full-suite long-context evaluations. Results are reported for LongBench v1, AA-LCR, NIAH, and RULER groupings up to 256k context.
|