Hugging Face's logo

qualcomm
/
Llama-v3.2-3B-Instruct-SSD

Text Generation
PyTorch
llm
generative_ai
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
aa7689d
·
verified ·
1 Parent(s): 713850a

v0.53.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.53.0 for changelog.

Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -51,10 +51,14 @@ See our repository for [Llama-v3.2-3B-Instruct-SSD on GitHub](https://github.com
51
  | Model | Runtime | Precision | Chipset | Context Length | Response Rate (tokens per second) | Time To First Token (range, seconds)
52
  |---|---|---|---|---|---|---
53
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4096 | 57.81013984680176 | 0.050954099999999995 - 1.6305311999999998
 
 
54
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® X2 Elite | 4096 | 78.08206481933594 | 0.05171440000000001 - 1.6548608000000002
55
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® X Elite | 4096 | 25.715454292297363 | 0.1213954 - 3.8846528
 
 
 
56
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Qualcomm® SA8775P | 4096 | 26.860780715942383 | 0.10895300000000001 - 3.4864960000000003
57
- | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4096 | 49.483089447021484 | 0.06807479999999999 - 2.1783935999999997
58
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Qualcomm® QCS9075 | 4096 | 33.729867935180664 | 0.10230380000000001 - 3.2737216000000005
59
 
60
  ## License
 
51
  | Model | Runtime | Precision | Chipset | Context Length | Response Rate (tokens per second) | Time To First Token (range, seconds)
52
  |---|---|---|---|---|---|---
53
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4096 | 57.81013984680176 | 0.050954099999999995 - 1.6305311999999998
54
+ | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® 8 Elite Mobile | 4096 | 49.483089447021484 | 0.06807479999999999 - 2.1783935999999997
55
+ | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® 8 Elite Mobile | 4096 | 49.483089447021484 | 0.06807479999999999 - 2.1783935999999997
56
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® X2 Elite | 4096 | 78.08206481933594 | 0.05171440000000001 - 1.6548608000000002
57
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® X Elite | 4096 | 25.715454292297363 | 0.1213954 - 3.8846528
58
+ | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Snapdragon® X Elite | 4096 | 25.715454292297363 | 0.1213954 - 3.8846528
59
+ | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Qualcomm® SA8775P | 4096 | 26.860780715942383 | 0.10895300000000001 - 3.4864960000000003
60
+ | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Qualcomm® SA8775P | 4096 | 26.860780715942383 | 0.10895300000000001 - 3.4864960000000003
61
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Qualcomm® SA8775P | 4096 | 26.860780715942383 | 0.10895300000000001 - 3.4864960000000003
 
62
  | Llama-v3.2-3B-Instruct-SSD | GENIE | w4a16 | Qualcomm® QCS9075 | 4096 | 33.729867935180664 | 0.10230380000000001 - 3.2737216000000005
63
 
64
  ## License