本文摘要本文基于WorkBuddy当前可用的本地部署大模型的配置参数,做总结,帮助大家高效使用本地算力资源,节省开销!

LuffyTheFox/qwen3.6-35b-a3b-uncensored-genesis-hermes-v6
| 字段 | 值 |
|---|---|
| name | LuffyTheFox/qwen3.6-35b-a3b-uncensored-genesis-hermes-v6 |
| id | qwen3.6-35b-a3b-uncensored-genesis-hermes-v6 |
| vendor | LM Studio |
| url | http://127.0.0.1:1234/v1/chat/completions |
| apiKey | lm-studio-key(任意即可,本地部署无需apikey) |
| disabled | false |
| maxInputTokens | 131072 |
| maxOutputTokens | 32768 |
| supportsToolCall | true |
| supportsImages | false(非 VL 视觉模型) |
| supportsReasoning | true |
| useCustomProtocol | false |
google/google/gemma-4-26b-a4b-qat
| 字段 | 值 |
|---|---|
| name | google/gemma-4-26b-a4b-qat |
| id | google/gemma-4-26b-a4b-qat |
| vendor | LM Studio |
| url | http://127.0.0.1:1234/v1/chat/completions |
| apiKey | lm-studio-key(任意即可,本地部署无需apikey) |
| disabled | false |
| maxInputTokens | 128000 |
| maxOutputTokens | 8192 |
| supportsToolCall | false |
| supportsImages | false(非 VL 视觉模型) |
| supportsReasoning | true |
| useCustomProtocol | false |
本文基于WorkBuddy当前可用的本地部署大模型的配置参数,做总结,帮助大家高效使用本地算力资源,节省开销!
觉得内容不错?我要