arturo-fredes commited on
Commit
015182a
·
verified ·
1 Parent(s): fa687d6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -6
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.