[GH-ISSUE #245] I suggest adding a 512G ram, 480G vram, 10 card optimization script #149

New issue

Closed

opened 2026-10-29 14:35:00 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-29 14:35:00 +00:00

Owner

Originally created by @Zha-Miku on GitHub (Feb 14, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/245

A quantitative version of Q4's deepseek-r1671b was used

Pure ollama runs in garbled code, but doesn't run in full parameters

Quantitative models require at least 1T of memory

Originally created by @Zha-Miku on GitHub (Feb 14, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/245 A quantitative version of Q4's deepseek-r1671b was used Pure ollama runs in garbled code, but doesn't run in full parameters Quantitative models require at least 1T of memory

bsakaguchi

2026-10-29 14:35:00 +00:00

closed this issue
added the
stale
label

bsakaguchi commented

2026-10-29 14:35:01 +00:00

Author

Owner

@Atream commented on GitHub (Feb 14, 2025):

We are working on it.

@Atream commented on GitHub (Feb 14, 2025): We are working on it.

bsakaguchi commented

2026-10-29 14:35:01 +00:00

Author

Owner

@ErvinXie commented on GitHub (Dec 11, 2025):

This issue has been automatically closed due to inactivity for 60 days.

If you believe this issue is still relevant, please feel free to reopen it with additional information or context.

Thank you for your contribution to KTransformers!

此 issue 因超过 60 天无活动而被自动关闭。

如果您认为此问题仍然存在，请随时重新打开并提供更多信息或上下文。

感谢您对 KTransformers 的贡献！

@ErvinXie commented on GitHub (Dec 11, 2025): This issue has been automatically closed due to inactivity for 60 days. If you believe this issue is still relevant, please feel free to reopen it with additional information or context. Thank you for your contribution to KTransformers! --- 此 issue 因超过 60 天无活动而被自动关闭。如果您认为此问题仍然存在，请随时重新打开并提供更多信息或上下文。感谢您对 KTransformers 的贡献！