G4 26B SFT v3 needs about 31.2 GB of memory at Q6_K (a 22.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 22.6 GB (Q6_K) to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
G4 26B SFT v3 is a 25.2B-parameter Sft model in GGUF format, quantized by ApocalypseParty. Its trained context length is 256K tokens. The repository has 2 quant files, from 22.6 GB (Q6_K) to 26.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 22.6 GB | 31.2 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 35.4 GB | Too big | Get file → |
What GPU do you need for G4 26B SFT v3?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).
Which G4 26B SFT v3 quant should you choose?
Q6_K (22.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about G4 26B SFT v3
How much VRAM does G4 26B SFT v3 need?
About 31.2 GB at Q6_K with an 8K context window. That is the 22.6 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 G4 26B SFT v3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 31.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of G4 26B SFT v3 GGUF?
It depends on the quant: Q6_K is 22.6 GB, Q8_0 is 26.9 GB.
What context length does G4 26B SFT v3 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download G4 26B SFT v3 GGUF?
The files are on Hugging Face in the ApocalypseParty/G4-26B-SFT-v3-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 G4 26B SFT v3 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.