Quen2 65B i1 needs about 44.4 GB of memory at Q4_K_M (a 41.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 20 quants, from 20.0 GB (IQ1_S) to 47.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.
Quen2 65B i1 is a 63.9B-parameter Quen model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 20 quant files, from 20.0 GB (IQ1_S) to 47.8 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 20.0 GB | 22.9 GB | Too big | Get file → | |
| IQ1_M | 20.9 GB | 23.8 GB | Too big | Get file → | |
| IQ2_XXS | 22.5 GB | 25.3 GB | Too big | Get file → | |
| IQ2_XS | 23.8 GB | 26.7 GB | Too big | Get file → | |
| IQ2_S | 24.6 GB | 27.5 GB | Too big | Get file → | |
| IQ2_M | 25.8 GB | 28.7 GB | Too big | Get file → | |
| Q2_K | 26.2 GB | 29.0 GB | Too big | Get file → | |
| IQ3_XXS | 28.0 GB | 30.8 GB | Too big | Get file → | |
| IQ3_XS | 28.8 GB | 31.7 GB | Too big | Get file → | |
| Q3_K_S | 30.2 GB | 33.1 GB | Too big | Get file → | |
| IQ3_S | 30.3 GB | 33.1 GB | Too big | Get file → | |
| IQ3_M | 31.2 GB | 34.0 GB | Too big | Get file → | |
| Q3_K_M | 33.1 GB | 35.9 GB | Too big | Get file → | |
| Q3_K_L | 34.8 GB | 37.6 GB | Too big | Get file → | |
| IQ4_XS | 35.0 GB | 37.8 GB | Too big | Get file → | |
| Q4_0 | 36.4 GB | 39.3 GB | Too big | Get file → | |
| Q4_K_S | 38.5 GB | 41.4 GB | Too big | Get file → | |
| Q4_K_M | 41.6 GB | 44.4 GB | Too big | Get file → | |
| Q5_K_S | 45.2 GB | 48.0 GB | Too big | Get file → | |
| Q5_K_M | 47.8 GB | 50.6 GB | Too big | Get file → |
What GPU do you need for Quen2 65B i1?
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 IQ1_M (20.9 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XS (28.8 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_S (45.2 GB file, about 48.0 GB in use).
Which Quen2 65B i1 quant should you choose?
Q4_K_M is the usual starting point for Quen2 65B i1: it balances file size and quality well. Here it is a 41.6 GB file.
If memory is tight, the smallest file is IQ1_S at 20.0 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 Quen2 65B i1
How much VRAM does Quen2 65B i1 need?
About 44.4 GB at Q4_K_M with an 8K context window. That is the 41.6 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 Quen2 65B i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Quen2 65B i1 GGUF?
It depends on the quant: IQ1_S is 20.0 GB, IQ1_M is 20.9 GB, IQ2_XXS is 22.5 GB, IQ2_XS is 23.8 GB, IQ2_S is 24.6 GB, IQ2_M is 25.8 GB and 14 more.
What context length does Quen2 65B i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.4 GB at 32K.
Where can I download Quen2 65B i1 GGUF?
The files are on Hugging Face in the mradermacher/Quen2-65B-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 Quen2 65B i1 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.