G3 Heresy MPOA G W99 D0.1838 R01 needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 13 quants, from 11.6 GB (IQ3_XS) to 54.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
G3 Heresy MPOA G W99 D0.1838 R01 is a 27B-parameter Heresy model in GGUF format, quantized by spikymoth. Its trained context length is 128K tokens. The repository has 13 quant files, from 11.6 GB (IQ3_XS) to 54.0 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 11.6 GB | 16.2 GB | Too big | Get file → | |
| IQ3_S | 12.2 GB | 16.8 GB | Too big | Get file → | |
| Q3_K_M | 13.4 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_L | 14.5 GB | 19.2 GB | Too big | Get file → | |
| IQ4_XS | 14.9 GB | 19.6 GB | Too big | Get file → | |
| IQ4_NL | 15.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_S | 15.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 21.2 GB | Too big | Get file → | |
| Q5_K_S | 18.8 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_M | 19.3 GB | 23.9 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 26.8 GB | Too big | Get file → | |
| Q8_0 | 28.7 GB | 33.4 GB | Too big | Get file → | |
| BF16 | 54.0 GB | 58.7 GB | Too big | Get file → |
What GPU do you need for G3 Heresy MPOA G W99 D0.1838 R01?
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: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).
Which G3 Heresy MPOA G W99 D0.1838 R01 quant should you choose?
Q4_K_M is the usual starting point for G3 Heresy MPOA G W99 D0.1838 R01: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.7 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 IQ3_XS at 11.6 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
Frequently asked questions about G3 Heresy MPOA G W99 D0.1838 R01
How much VRAM does G3 Heresy MPOA G W99 D0.1838 R01 need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 G3 Heresy MPOA G W99 D0.1838 R01 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of G3 Heresy MPOA G W99 D0.1838 R01 GGUF?
It depends on the quant: IQ3_XS is 11.6 GB, IQ3_S is 12.2 GB, Q3_K_M is 13.4 GB, Q3_K_L is 14.5 GB, IQ4_XS is 14.9 GB, IQ4_NL is 15.7 GB and 7 more.
What context length does G3 Heresy MPOA G W99 D0.1838 R01 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download G3 Heresy MPOA G W99 D0.1838 R01 GGUF?
The files are on Hugging Face in the spikymoth/G3-Heresy-MPOA-G-W99-D0.1838-R01-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.