Downloads · 30 days
8
2% of all-time downloads
DeepSeek-R1-0528-optimized-for-512Gb-GGUF
mmbela/DeepSeek-R1-0528-optimized-for-512Gb-GGUF
DeepSeek-R1-0528-optimized-for-512Gb-GGUF is a machine learning model from mmbela. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This model is a merge of three differently quantized models from the unsloth/DeepSeek-R1-0528-GGUF repository. Everything except the routed experts comes from Q80, while most routed experts come from UD-Q4-XL and 6 mo…
All-time downloads
352
Public
Repo size
521 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf521 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 4, 2025
- Updated
- Jun 6, 2025
- SHA
- 34a4aae4
Base models
Model card
From the Hugging Face model README
This model is a merge of three differently quantized models from the unsloth/DeepSeek-R1-0528-GGUF repository. Everything except the routed experts comes from Q8_0, while most routed experts come from UD-Q4-XL and 6 more critical block routed experts originate from UD-Q5-XL.
After setting on Mac "sudo sysctl iogpu.wired_limit_mb=516096", my tests show it achieves maximum performance with a 16k context window under this size constraint. A 16k context window is often more than enough. Of course, those with more memory can opt for a larger one. It's clearly much smarter than homogeneous quantized versions of the same size.
- License
- mit
- Created
- Jun 4, 2025
- Updated
- Jun 6, 2025