[GH-ISSUE #1679] 请问在 RTX 5090 32GB 上,最多能部署哪个 Qwen 模型? #1077

Closed
opened 2026-10-29 14:48:16 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @jiayuchou on GitHub (Dec 8, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1679

Reminder

  • I have read the above rules and searched the existing issues.

Description

我想确认在我的机器上能部署的 Qwen 模型上限。

我的硬件:

GPU:RTX 5090 32GB

CPU:Intel Xeon W7-2475X(20 核 40 线程)

内存:64GB DDR5

存储:1TB SSD(M.2 可用)

请问在你们的框架中,我最多可以运行到 Qwen 的哪个模型规模(如 14B、32B、72B)?
如果使用 4-bit / 8-bit 量化或 offload,有推荐的配置吗?

谢谢!

Pull Request

No response

Originally created by @jiayuchou on GitHub (Dec 8, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1679 ### Reminder - [x] I have read the above rules and searched the existing issues. ### Description 我想确认在我的机器上能部署的 Qwen 模型上限。 我的硬件: GPU:RTX 5090 32GB CPU:Intel Xeon W7-2475X(20 核 40 线程) 内存:64GB DDR5 存储:1TB SSD(M.2 可用) 请问在你们的框架中,我最多可以运行到 Qwen 的哪个模型规模(如 14B、32B、72B)? 如果使用 4-bit / 8-bit 量化或 offload,有推荐的配置吗? 谢谢! ### Pull Request _No response_
bsakaguchi 2026-10-29 14:48:16 +00:00
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
kvcache-ai/ktransformers#1077
No description provided.