| model_family,model,type,batch,device,res,fps,frames,e2e,tps,tpot,ttft |
| Llama-3.2-1B,meta-llama/Llama-3.2-1B-Instruct,text,1,agx_thor,N/A,N/A,N/A,3.3117,77.30,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead,text,1,agx_thor,N/A,N/A,N/A,2.6227,97.61,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead-W4A16,text,1,agx_thor,N/A,N/A,N/A,0.8990,284.76,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-W4A16,text,1,agx_thor,N/A,N/A,N/A,1.5758,162.46,N/A,N/A |
| Llama-3.2-3B,meta-llama/Llama-3.2-3B-Instruct,text,1,agx_thor,N/A,N/A,N/A,7.4843,34.21,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-FlashHead,text,1,agx_thor,N/A,N/A,N/A,6.3909,40.06,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-FlashHead-W4A16,text,1,agx_thor,N/A,N/A,N/A,2.2935,111.62,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-W4A16,text,1,agx_thor,N/A,N/A,N/A,3.4786,73.59,N/A,N/A |
| Llama-3.2-3B,meta-llama/Llama-3.2-3B-Instruct,text,1,agx_orin,N/A,N/A,N/A,9.9847,25.64,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-FlashHead,text,1,agx_orin,N/A,N/A,N/A,9.1964,27.84,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-FlashHead-W4A16,text,1,agx_orin,N/A,N/A,N/A,3.3957,75.39,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-W4A16,text,1,agx_orin,N/A,N/A,N/A,4.1822,61.21,N/A,N/A |
| Llama-3.2-1B,meta-llama/Llama-3.2-1B-Instruct,text,1,agx_orin,N/A,N/A,N/A,3.9372,65.02,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead,text,1,agx_orin,N/A,N/A,N/A,3.4045,75.19,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead-W4A16,text,1,agx_orin,N/A,N/A,N/A,1.3120,195.12,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-W4A16,text,1,agx_orin,N/A,N/A,N/A,1.8475,138.57,N/A,N/A |
| Llama-3.2-1B,meta-llama/Llama-3.2-1B-Instruct,text,1,orin_nano_super,N/A,N/A,N/A,6.8469,37.39,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead,text,1,orin_nano_super,N/A,N/A,N/A,5.8939,43.43,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead-W4A16,text,1,orin_nano_super,N/A,N/A,N/A,2.2979,111.41,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-W4A16,text,1,orin_nano_super,N/A,N/A,N/A,3.2571,78.60,N/A,N/A |
| Llama-3.2-1B,meta-llama/Llama-3.2-1B-Instruct,text,1,rtx_3500_ada,N/A,N/A,N/A,,130.00,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead,text,1,rtx_3500_ada,N/A,N/A,N/A,,163.00,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-W4A16,text,1,rtx_3500_ada,N/A,N/A,N/A,,278.00,N/A,N/A |
| Llama-3.2-1B,embedl/Llama-3.2-1B-Instruct-FlashHead-W4A16,text,1,rtx_3500_ada,N/A,N/A,N/A,,485.00,N/A,N/A |
| Llama-3.2-3B,meta-llama/Llama-3.2-3B-Instruct,text,1,rtx_3500_ada,N/A,N/A,N/A,,54.00,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-FlashHead,text,1,rtx_3500_ada,N/A,N/A,N/A,,58.00,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-W4A16,text,1,rtx_3500_ada,N/A,N/A,N/A,,141.00,N/A,N/A |
| Llama-3.2-3B,embedl/Llama-3.2-3B-Instruct-FlashHead-W4A16,text,1,rtx_3500_ada,N/A,N/A,N/A,,177.00,N/A,N/A |
|
|