DeepSeek V3.2 REAP 345B A37B GGUF Experimental needs about 112.2 GB of memory at IQ1_S (a 99.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 0.5 GB to 123.2 GB (Q2_K).
DeepSeek V3.2 REAP 345B A37B GGUF Experimental is a 344B-parameter DeepSeek model in GGUF format, quantized by lovedheart. Its trained context length is 160K tokens. The repository has 5 quant files, from 0.5 GB to 123.2 GB (Q2_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ1_S | 85.7 GB (236 parts) | 96.4 GB | Too big | Get file → | |
| IQ1_S | 99.7 GB (236 parts) | 112.2 GB | Too big | Get file → | |
| IQ1_M | 101.3 GB (236 parts) | 113.9 GB | Too big | Get file → | |
| Q2_K | 123.2 GB (236 parts) | 138.4 GB | Too big | Get file → |
What GPU do you need for DeepSeek V3.2 REAP 345B A37B GGUF Experimental?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.1 GB in use).
Which DeepSeek V3.2 REAP 345B A37B GGUF Experimental quant should you choose?
IQ1_S (99.7 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V3.2 REAP 345B A37B GGUF Experimental
How much VRAM does DeepSeek V3.2 REAP 345B A37B GGUF Experimental need?
About 112.2 GB at IQ1_S with an 8K context window. That is the 99.7 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 DeepSeek V3.2 REAP 345B A37B GGUF Experimental on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepSeek V3.2 REAP 345B A37B GGUF Experimental GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 85.7 GB, IQ1_S is 99.7 GB, IQ1_M is 101.3 GB, Q2_K is 123.2 GB.
What context length does DeepSeek V3.2 REAP 345B A37B GGUF Experimental support?
The GGUF header lists a trained context length of 163,840 tokens (160K).
Where can I download DeepSeek V3.2 REAP 345B A37B GGUF Experimental GGUF?
The files are on Hugging Face in the lovedheart/DeepSeek-V3.2-REAP-345B-A37B-GGUF-Experimental repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does DeepSeek V3.2 REAP 345B A37B GGUF Experimental use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.