Agents A1 needs about 26.5 GB of memory at Q3_0 (a 25.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 8 quants, from 19.3 GB (Q3_0) to 36.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Agents A1 is a 34.7B-parameter Agents model in GGUF format, quantized by rcmorano. Its trained context length is 256K tokens. The repository has 8 quant files, from 19.3 GB (Q3_0) to 36.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_0 | 19.3 GB | 20.5 GB | Too big | Get file → | |
| Q4_0 | 19.7 GB | 20.9 GB | Too big | Get file → | |
| Q4_0 | 22.7 GB | 23.9 GB | Too big | Get file → | |
| Q3_0 | 25.4 GB | 26.5 GB | Too big | Get file → | |
| Q6_0 | 28.7 GB | 29.8 GB | Too big | Get file → | |
| Q6_0 | 32.3 GB | 33.4 GB | Too big | Get file → | |
| Q8_0 | 35.8 GB | 37.0 GB | Too big | Get file → | |
| Q8_0 | 36.4 GB | 37.6 GB | Too big | Get file → |
What GPU do you need for Agents A1?
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 Q4_0 (22.7 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_0 (28.7 GB file, about 29.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.4 GB file, about 37.6 GB in use).
Which Agents A1 quant should you choose?
Q3_0 (25.4 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q3_0 at 19.3 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 Agents A1
How much VRAM does Agents A1 need?
About 26.5 GB at Q3_0 with an 8K context window. That is the 25.4 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 Agents A1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Agents A1 GGUF?
It depends on the quant: Q3_0 is 19.3 GB, Q4_0 is 19.7 GB, Q4_0 is 22.7 GB, Q3_0 is 25.4 GB, Q6_0 is 28.7 GB, Q6_0 is 32.3 GB and 2 more.
What context length does Agents A1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Agents A1 GGUF?
The files are on Hugging Face in the rcmorano/InternScience-Agents-A1-ROCMFPX repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Agents A1 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.