Aquif 3.5 Max 42B A3B needs about 27.3 GB of memory at Q4_K_M (a 25.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.2 GB to 34.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.5 GB.
Aquif 3.5 Max 42B A3B is a 42.4B-parameter Aquif model in GGUF format, quantized by mradermacher. Its trained context length is 986K tokens. The repository has 24 quant files, from 0.2 GB to 34.8 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 8.8 GB | 10.4 GB | Too big | Get file → | |
| IQ1_M | 9.7 GB | 11.4 GB | Too big | Get file → | |
| IQ2_XXS | 11.3 GB | 12.9 GB | Too big | Get file → | |
| IQ2_XS | 12.5 GB | 14.2 GB | Too big | Get file → | |
| IQ2_S | 12.8 GB | 14.4 GB | Too big | Get file → | |
| IQ2_M | 14.0 GB | 15.7 GB | Too big | Get file → | |
| Q2_K_S | 14.5 GB | 16.1 GB | Too big | Get file → | |
| Q2_K | 15.6 GB | 17.2 GB | Too big | Get file → | |
| IQ3_XXS | 16.4 GB | 18.0 GB | Too big | Get file → | |
| IQ3_XS | 17.4 GB | 19.1 GB | Too big | Get file → | |
| Q3_K_S | 18.4 GB | 20.0 GB | Too big | Get file → | |
| IQ3_S | 18.4 GB | 20.0 GB | Too big | Get file → | |
| IQ3_M | 18.7 GB | 20.3 GB | Too big | Get file → | |
| Q3_K_M | 20.4 GB | 22.0 GB | Too big | Get file → | |
| Q3_K_L | 22.0 GB | 23.7 GB | Too big | Get file → | |
| IQ4_XS | 22.7 GB | 24.3 GB | Too big | Get file → | |
| Q4_0 | 24.1 GB | 25.7 GB | Too big | Get file → | |
| Q4_K_S | 24.2 GB | 25.8 GB | Too big | Get file → | |
| Q4_K_M | 25.7 GB | 27.3 GB | Too big | Get file → | |
| Q4_1 | 26.6 GB | 28.2 GB | Too big | Get file → | |
| Q5_K_S | 29.2 GB | 30.9 GB | Too big | Get file → | |
| Q5_K_M | 30.1 GB | 31.7 GB | Too big | Get file → | |
| Q6_K | 34.8 GB | 36.4 GB | Too big | Get file → |
What GPU do you need for Aquif 3.5 Max 42B A3B?
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 the main file (0.2 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.8 GB in use).
- 12 GB VRAM: the best quant that fits is IQ1_M (9.7 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_M (14.0 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_L (22.0 GB file, about 23.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (30.1 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (34.8 GB file, about 36.4 GB in use).
Which Aquif 3.5 Max 42B A3B quant should you choose?
Q4_K_M is the usual starting point for Aquif 3.5 Max 42B A3B: it balances file size and quality well. Here it is a 25.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Aquif 3.5 Max 42B A3B
How much VRAM does Aquif 3.5 Max 42B A3B need?
About 27.3 GB at Q4_K_M with an 8K context window. That is the 25.7 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 Aquif 3.5 Max 42B A3B on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Aquif 3.5 Max 42B A3B GGUF?
It depends on the quant: file is 0.2 GB, IQ1_S is 8.8 GB, IQ1_M is 9.7 GB, IQ2_XXS is 11.3 GB, IQ2_XS is 12.5 GB, IQ2_S is 12.8 GB and 18 more.
What context length does Aquif 3.5 Max 42B A3B support?
The GGUF header lists a trained context length of 1,010,000 tokens (986K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.5 GB at 32K.
Where can I download Aquif 3.5 Max 42B A3B GGUF?
The files are on Hugging Face in the mradermacher/aquif-3.5-Max-42B-A3B-i1-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 Aquif 3.5 Max 42B A3B 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.