Deep Seek R1 32B CSCEC LoRa needs about 12.4 GB of memory at TQ1_0 (a 9.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 9.7 GB (TQ1_0) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Deep Seek R1 32B CSCEC LoRa is a 32.8B-parameter Deep model in GGUF format, quantized by jacytong. Its trained context length is 128K tokens. The repository has 2 quant files, from 9.7 GB (TQ1_0) to 34.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 9.7 GB | 12.4 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 37.5 GB | Too big | Get file → |
What GPU do you need for Deep Seek R1 32B CSCEC LoRa?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is TQ1_0 (9.7 GB file, about 12.4 GB in use).
- 24 GB VRAM: the best quant that fits is TQ1_0 (9.7 GB file, about 12.4 GB in use).
- 32 GB VRAM: the best quant that fits is TQ1_0 (9.7 GB file, about 12.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).
Which Deep Seek R1 32B CSCEC LoRa quant should you choose?
TQ1_0 (9.7 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Deep Seek R1 32B CSCEC LoRa
How much VRAM does Deep Seek R1 32B CSCEC LoRa need?
About 12.4 GB at TQ1_0 with an 8K context window. That is the 9.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Deep Seek R1 32B CSCEC LoRa on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Deep Seek R1 32B CSCEC LoRa GGUF?
It depends on the quant: TQ1_0 is 9.7 GB, Q8_0 is 34.8 GB.
What context length does Deep Seek R1 32B CSCEC LoRa support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Deep Seek R1 32B CSCEC LoRa GGUF?
The files are on Hugging Face in the jacytong/Deep-Seek-R1-32B-CSCEC-LoRa repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Deep Seek R1 32B CSCEC LoRa use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.