DavidAU Gemma The Writer DEADLINE 10B needs about 9.8 GB of memory at Q4_K_M (a 6.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 19 quants, from 1.0 GB (IQ4_NL) to 10.7 GB (Q8_0).
DavidAU Gemma The Writer DEADLINE 10B is a 9B-parameter Gemma model in GGUF format, quantized by Kaiser5976. Its trained context length is 8K tokens. The repository has 19 quant files, from 1.0 GB (IQ4_NL) to 10.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 1.0 GB | 4.6 GB | Fits | Get file → | |
| IQ4_XS | 3.2 GB | 6.8 GB | Fits | Get file → | |
| Q2_K | 4.1 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_S | 4.7 GB | 8.3 GB | Too big | Get file → | |
| Q3_K | 5.1 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 5.1 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_L | 5.5 GB | 9.1 GB | Too big | Get file → | |
| Q4_0 | 5.9 GB | 9.5 GB | Too big | Get file → | |
| Q4_K_S | 5.9 GB | 9.5 GB | Too big | Get file → | |
| Q4_K | 6.2 GB | 9.8 GB | Too big | Get file → | |
| Q4_K_M | 6.2 GB | 9.8 GB | Too big | Get file → | |
| Q4_1 | 6.5 GB | 10.0 GB | Too big | Get file → | |
| Q5_0 | 7.0 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_S | 7.0 GB | 10.6 GB | Too big | Get file → | |
| Q5_K | 7.2 GB | 10.8 GB | Too big | Get file → | |
| Q5_K_M | 7.2 GB | 10.8 GB | Too big | Get file → | |
| Q5_1 | 7.6 GB | 11.2 GB | Too big | Get file → | |
| Q6_K | 8.2 GB | 11.8 GB | Too big | Get file → | |
| Q8_0 | 10.7 GB | 14.3 GB | Too big | Get file → |
What GPU do you need for DavidAU Gemma The Writer DEADLINE 10B?
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: the best quant that fits is IQ4_NL (1.0 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K (4.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (8.2 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (10.7 GB file, about 14.3 GB in use).
Which DavidAU Gemma The Writer DEADLINE 10B quant should you choose?
Q4_K_M is the usual starting point for DavidAU Gemma The Writer DEADLINE 10B: it balances file size and quality well. Here it is a 6.2 GB file.
The Q8_0 file is 10.7 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 IQ4_NL at 1.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about DavidAU Gemma The Writer DEADLINE 10B
How much VRAM does DavidAU Gemma The Writer DEADLINE 10B need?
About 9.8 GB at Q4_K_M with an 8K context window. That is the 6.2 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 DavidAU Gemma The Writer DEADLINE 10B on an 8 GB GPU?
Yes, with Q2_K: the 4.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DavidAU Gemma The Writer DEADLINE 10B GGUF?
It depends on the quant: IQ4_NL is 1.0 GB, IQ4_XS is 3.2 GB, Q2_K is 4.1 GB, Q3_K_S is 4.7 GB, Q3_K is 5.1 GB, Q3_K_M is 5.1 GB and 13 more.
What context length does DavidAU Gemma The Writer DEADLINE 10B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.
Where can I download DavidAU Gemma The Writer DEADLINE 10B GGUF?
The files are on Hugging Face in the Kaiser5976/DavidAU_-_Gemma-The-Writer-DEADLINE-10B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.