dihem v3 pro needs about 3.1 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.
dihem v3 pro is a 2.61B-parameter Dihem model in GGUF format, quantized by dihem07. Its trained context length is 8K tokens. The repository has 1 quant file, from 1.7 GB (Q4_K_M) to 1.7 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.7 GB | 3.1 GB | Fits | Get file → |
What GPU do you need for dihem v3 pro?
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: the best quant that fits is Q4_K_M (1.7 GB file, about 3.1 GB in use).
Which dihem v3 pro quant should you choose?
Q4_K_M is the usual starting point for dihem v3 pro: it balances file size and quality well. Here it is a 1.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about dihem v3 pro
How much VRAM does dihem v3 pro need?
About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.7 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 dihem v3 pro on an 8 GB GPU?
Yes, with Q4_K_M: the 1.7 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of dihem v3 pro GGUF?
It depends on the quant: Q4_K_M is 1.7 GB.
What context length does dihem v3 pro support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.
Where can I download dihem v3 pro GGUF?
The files are on Hugging Face in the dihem07/dihem-v3-pro repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.