wehub-resource-sync
51 lines
1.6 KiB
JSON
51 lines
1.6 KiB
JSON
{
|
|
"device": "android",
|
|
"model_list": [
|
|
{
|
|
"model": "HF://mlc-ai/Phi-3.5-mini-instruct-q4f16_0-MLC",
|
|
"estimated_vram_bytes": 4250586449,
|
|
"model_id": "Phi-3.5-mini-instruct-q4f16_0-MLC",
|
|
"overrides": {
|
|
"prefill_chunk_size": 128
|
|
}
|
|
},
|
|
{
|
|
"model": "HF://mlc-ai/Qwen3-0.6B-q0f16-MLC",
|
|
"model_id": "Qwen3-0.6B-q0f16-MLC",
|
|
"estimated_vram_bytes": 3000000000,
|
|
"overrides": {
|
|
"prefill_chunk_size": 128,
|
|
"context_window_size": 2048
|
|
}
|
|
},
|
|
{
|
|
"model": "HF://mlc-ai/Qwen3-1.7B-q4f16_1-MLC",
|
|
"model_id": "Qwen3-1.7B-q4f16_1-MLC",
|
|
"estimated_vram_bytes": 3000000000,
|
|
"overrides": {
|
|
"prefill_chunk_size": 128,
|
|
"context_window_size": 2048
|
|
}
|
|
},
|
|
{
|
|
"model": "HF://mlc-ai/gemma-2-2b-it-q4f16_1-MLC",
|
|
"model_id": "gemma-2-2b-it-q4f16_1-MLC",
|
|
"estimated_vram_bytes": 3000000000
|
|
},
|
|
{
|
|
"model": "HF://mlc-ai/Llama-3.2-3B-Instruct-q4f16_0-MLC",
|
|
"estimated_vram_bytes": 4679979417,
|
|
"model_id": "Llama-3.2-3B-Instruct-q4f16_0-MLC"
|
|
},
|
|
{
|
|
"model": "HF://mlc-ai/Mistral-7B-Instruct-v0.3-q4f16_1-MLC",
|
|
"estimated_vram_bytes": 4115131883,
|
|
"model_id": "Mistral-7B-Instruct-v0.3-q4f16_1-MLC",
|
|
"overrides": {
|
|
"sliding_window_size": 768,
|
|
"prefill_chunk_size": 256
|
|
}
|
|
}
|
|
]
|
|
}
|