Holger 7B v0.1 needs about 9.4 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 9 quants, from 4.1 GB (Q3_K_L) to 15.1 GB (F16).
Holger 7B v0.1 is a 7.55B-parameter Holger model in GGUF format, quantized by trollek. Its trained context length is 4K tokens. The repository has 9 quant files, from 4.1 GB (Q3_K_L) to 15.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 4.1 GB | 6.8 GB | Fits | Get file → | |
| Q4_0 | 4.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_S | 4.4 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 4.6 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_S | 5.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 5.4 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 6.2 GB | 8.8 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 10.7 GB | Too big | Get file → | |
| F16 | 15.1 GB | 17.8 GB | Too big | Get file → |
What GPU do you need for Holger 7B v0.1?
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: the best quant that fits is Q6_K (6.2 GB file, about 11.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 12.8 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.1 GB file, about 19.9 GB in use).
Which Holger 7B v0.1 quant should you choose?
Q4_K_M is the usual starting point for Holger 7B v0.1: it balances file size and quality well. Here it is a 4.6 GB file.
The Q8_0 file is 8.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_L at 4.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Holger 7B v0.1
How much VRAM does Holger 7B v0.1 need?
About 9.4 GB at Q4_K_M with an 8K context window. That is the 4.6 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 Holger 7B v0.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Holger 7B v0.1 GGUF?
It depends on the quant: Q3_K_L is 4.1 GB, Q4_0 is 4.4 GB, Q4_K_S is 4.4 GB, Q4_K_M is 4.6 GB, Q5_K_S is 5.3 GB, Q5_K_M is 5.4 GB and 3 more.
What context length does Holger 7B v0.1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download Holger 7B v0.1 GGUF?
The files are on Hugging Face in the trollek/Holger-7B-v0.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Holger 7B v0.1 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.