LiquidAI
/

LFM2.5-1.2B-Instruct

Text Generation

Model card Files Files and versions

mlabonne commited on 11 days ago

Commit

8dc4e68

·

verified ·

1 Parent(s): 47c527b

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -201,7 +201,8 @@ LFM2.5-1.2B-Instruct offers extremely fast inference speed on CPUs with a low me
 ![image](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/dbbI-15p9re2ROhAkqnZm.png)
-In addition, we are partnering with AMD, Qualcomm, and Nexa AI to bring the LFM2.5 family to NPUs. These optimized models are available through our partners, enabling highly efficient on-device inference.
 | Device                                               | Inference | Framework        | Model                | Prefill (tok/s) | Decode (tok/s) | Memory (GB) |
 | ---------------------------------------------------- | --------- | ---------------- | -------------------- | --------------- | -------------- | ----------- |

 ![image](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/dbbI-15p9re2ROhAkqnZm.png)
+In addition, we are partnering with AMD, Qualcomm, and Nexa AI to bring the LFM2.5 family to NPUs. These optimized models are available through our partners, enabling highly efficient on-device inference.
+The following numbers have been calculated using 1K prefill and 100 decode tokens:
 | Device                                               | Inference | Framework        | Model                | Prefill (tok/s) | Decode (tok/s) | Memory (GB) |
 | ---------------------------------------------------- | --------- | ---------------- | -------------------- | --------------- | -------------- | ----------- |