2026驍龍峯會上，高通與PrismML在驍龍AR1 Gen 1智能眼鏡平臺本地運行20億參數1-bit量化Bonsai視覺模型，實現離線識圖問答。該模型基於Bonsai 1.7B構建，精度壓縮至1-bit，內存佔用僅爲4-bit模型四分之一，同等內存可容納約4倍參數，顯著降低存儲與推理資源需求。
全球首個27B級手機AI模型Bonsai27B問世，基於Qwen3.6，採用三進制與二進制壓縮技術：三元版5.9GB側重性能，可在筆記本運行；1-bit版極致縮小，適配移動端。這一突破標誌着大模型輕量化部署的重大飛躍。
Xai
$1.4
輸入tokens/百萬
$3.5
輸出tokens/百萬
2k
上下文長度
Openai
$0.4
-
128
Huawei
32
Chatglm
Tencent
$0.5
$2
224
$1
$3
4
Bytedance
Deepseek
8
Alibaba
$6
$18
256
Baidu
$0.8
$3.2
01-ai
$0.99
legraphista
這是 DeepSeek-Coder-V2-Instruct 模型的 GGUF 量化版本，使用 llama.cpp 的 IMatrix 技術進行優化量化。該模型專門針對代碼生成和編程任務進行了優化，提供了從 1-bit 到 8-bit 的多種量化選項，適用於不同硬件環境下的高效推理。
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
VIP會員
