AquilaChat2 70B Expr needs about 45.4 GB of memory at Q4_K_M (a 42.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 26.1 GB (Q2_K) to 49.6 GB (Q5_K_M).
AquilaChat2 70B Expr is a 70.1B-parameter Aquilachat model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 12 quant files, from 26.1 GB (Q2_K) to 49.6 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 26.1 GB | 27.9 GB | Too big | Get file → | |
| IQ3_XS | 29.0 GB | 30.9 GB | Too big | Get file → | |
| IQ3_S | 30.6 GB | 32.5 GB | Too big | Get file → | |
| Q3_K_S | 30.6 GB | 32.5 GB | Too big | Get file → | |
| IQ3_M | 31.6 GB | 33.5 GB | Too big | Get file → | |
| Q3_K_M | 34.0 GB | 35.8 GB | Too big | Get file → | |
| Q3_K_L | 36.8 GB | 38.7 GB | Too big | Get file → | |
| IQ4_XS | 38.0 GB | 39.8 GB | Too big | Get file → | |
| Q4_K_S | 40.0 GB | 41.9 GB | Too big | Get file → | |
| Q4_K_M | 42.2 GB | 44.0 GB | Too big | Get file → | |
| Q5_K_S | 48.3 GB | 50.1 GB | Too big | Get file → | |
| Q5_K_M | 49.6 GB | 51.4 GB | Too big | Get file → |
What GPU do you need for AquilaChat2 70B Expr?
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 Q2_K (26.1 GB file, about 29.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (42.2 GB file, about 45.4 GB in use).
Which AquilaChat2 70B Expr quant should you choose?
Q4_K_M is the usual starting point for AquilaChat2 70B Expr: it balances file size and quality well. Here it is a 42.2 GB file.
If memory is tight, the smallest file is Q2_K at 26.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AquilaChat2 70B Expr
How much VRAM does AquilaChat2 70B Expr need?
About 45.4 GB at Q4_K_M with an 8K context window. That is the 42.2 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 AquilaChat2 70B Expr on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of AquilaChat2 70B Expr GGUF?
It depends on the quant: Q2_K is 26.1 GB, IQ3_XS is 29.0 GB, IQ3_S is 30.6 GB, Q3_K_S is 30.6 GB, IQ3_M is 31.6 GB, Q3_K_M is 34.0 GB and 6 more.
What context length does AquilaChat2 70B Expr support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download AquilaChat2 70B Expr GGUF?
The files are on Hugging Face in the mradermacher/AquilaChat2-70B-Expr-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 AquilaChat2 70B Expr use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.