ICONN E1 needs about 42.1 GB of memory at Q3_K_M (a 40.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 30.8 GB (Q2_K) to 47.8 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
ICONN E1 is a 84B-parameter Iconn model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 6 quant files, from 30.8 GB (Q2_K) to 47.8 GB (Q4_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 30.8 GB | 32.6 GB | Too big | Get file → | |
| Q3_K_S | 36.4 GB | 38.2 GB | Too big | Get file → | |
| Q3_K_M | 40.2 GB | 42.1 GB | Too big | Get file → | |
| Q3_K_L | 43.5 GB | 45.4 GB | Too big | Get file → | |
| IQ4_XS | 45.4 GB | 47.2 GB | Too big | Get file → | |
| Q4_K_S | 47.8 GB | 49.7 GB | Too big | Get file → |
What GPU do you need for ICONN E1?
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: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is IQ4_XS (45.4 GB file, about 47.2 GB in use).
Which ICONN E1 quant should you choose?
Q3_K_M (40.2 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 Q2_K at 30.8 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 ICONN E1
How much VRAM does ICONN E1 need?
About 42.1 GB at Q3_K_M with an 8K context window. That is the 40.2 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 ICONN E1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ICONN E1 GGUF?
It depends on the quant: Q2_K is 30.8 GB, Q3_K_S is 36.4 GB, Q3_K_M is 40.2 GB, Q3_K_L is 43.5 GB, IQ4_XS is 45.4 GB, Q4_K_S is 47.8 GB.
What context length does ICONN E1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download ICONN E1 GGUF?
The files are on Hugging Face in the mradermacher/ICONN-e1-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 ICONN E1 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.