| 47501 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-G64-AS-TK-ASYM-S12M05-KVH |
HuggingFace |
2.12 |
high |
| 47502 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-G64-AS-TK-SYM-S12M05-KVT |
HuggingFace |
2.12 |
high |
| 47503 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-128-AS-TOKEN-Wsym-Aasym-SpQ-R1R2R4-SmQ-0.5-KVS-tensor |
HuggingFace |
2.12 |
high |
| 47504 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-128-AS-TOKEN-Wsym-Aasym-SpQ-R1R2-SmQ-0.5-KVS-attn_head |
HuggingFace |
2.12 |
high |
| 47505 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-128-AS-TOKEN-Wsym-Asym-SpQ-R1R2R4-SmQ-0.5-KVS-tensor |
HuggingFace |
2.12 |
high |
| 47506 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-128-AS-TOKEN-Wsym-Asym-SpQ-R1R2-SmQ-0.5-KVS-attn_head |
HuggingFace |
2.12 |
high |
| 47507 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-128-AS-TOKEN-Wsym-Asym-SpQ-R1R2-SmQ-0.5-KVS-tensor |
HuggingFace |
2.12 |
high |
| 47508 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-32-AS-TOKEN-Wsym-Aasym-SpQ-R1R2R4-SmQ-0.5-KVS-tensor |
HuggingFace |
2.12 |
high |
| 47509 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-32-AS-TOKEN-Wsym-Aasym-SpQ-R1R2-SmQ-0.5-KVS-attn_head |
HuggingFace |
2.12 |
high |
| 47510 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-32-AS-TOKEN-Wsym-Asym-SpQ-R1R2R4-SmQ-0.5-KVS-attn_head |
HuggingFace |
2.12 |
high |
| 47511 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-64-AS-TOKEN-Wsym-Aasym-SpQ-R1R2R4-SmQ-0.5-KVS-tensor |
HuggingFace |
2.12 |
high |
| 47512 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-64-AS-TOKEN-Wsym-Aasym-SpQ-R1R2-SmQ-0.5-KVS-attn_head |
HuggingFace |
2.12 |
high |
| 47513 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-64-AS-TOKEN-Wsym-Asym-SpQ-R1R2R4-SmQ-0.5-KVS-attn_head |
HuggingFace |
2.12 |
high |
| 47514 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-64-AS-TOKEN-Wsym-Asym-SpQ-R1R2R4-SmQ-0.5-KVS-tensor |
HuggingFace |
2.12 |
high |
| 47515 |
Llama-3.1-8B-Instruct-W4A8KV8-WS-GROUP-GS-64-AS-TOKEN-Wsym-Asym-SpQ-R1R2-SmQ-0.5-KVS-tensor |
HuggingFace |
2.12 |
high |
| 47516 |
Llama-3.1-8B-Instruct-W8A16KV16-asym-GS-128 |
HuggingFace |
2.12 |
high |
| 47517 |
Llama-3.1-8B-Instruct-W8A16KV16-asym-GS-32 |
HuggingFace |
2.12 |
high |
| 47518 |
Llama-3.1-8B-Instruct-W8A16KV16-asym-GS-64 |
HuggingFace |
2.12 |
high |
| 47519 |
Llama-3.1-8B-Instruct-W8A16KV16-FP-WS-BLOCK-128x128 |
HuggingFace |
2.12 |
high |
| 47520 |
Llama-3.1-8B-Instruct-W8A16KV16-FP-WS-CHANNEL |
HuggingFace |
2.12 |
high |