Fusion 7B Quintessence i1 needs about 16.5 GB of memory at Q4_K_M (a 12.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.6 GB (IQ1_S) to 17.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Fusion 7B Quintessence i1 is a 21.2B-parameter Fusion model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 21 quant files, from 4.6 GB (IQ1_S) to 17.4 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.6 GB | 8.3 GB | Too big | Get file → | |
| IQ1_M | 5.0 GB | 8.7 GB | Too big | Get file → | |
| IQ2_XXS | 5.7 GB | 9.4 GB | Too big | Get file → | |
| IQ2_XS | 6.3 GB | 10.0 GB | Too big | Get file → | |
| IQ2_S | 6.6 GB | 10.4 GB | Too big | Get file → | |
| IQ2_M | 7.2 GB | 10.9 GB | Too big | Get file → | |
| Q2_K | 7.9 GB | 11.6 GB | Too big | Get file → | |
| IQ3_XXS | 8.2 GB | 11.9 GB | Too big | Get file → | |
| IQ3_XS | 8.7 GB | 12.4 GB | Too big | Get file → | |
| Q3_K_S | 9.2 GB | 12.9 GB | Too big | Get file → | |
| IQ3_S | 9.2 GB | 12.9 GB | Too big | Get file → | |
| IQ3_M | 9.5 GB | 13.2 GB | Too big | Get file → | |
| Q3_K_M | 10.2 GB | 13.9 GB | Too big | Get file → | |
| Q3_K_L | 11.1 GB | 14.9 GB | Too big | Get file → | |
| IQ4_XS | 11.4 GB | 15.1 GB | Too big | Get file → | |
| Q4_0 | 12.0 GB | 15.7 GB | Too big | Get file → | |
| Q4_K_S | 12.1 GB | 15.8 GB | Too big | Get file → | |
| Q4_K_M | 12.7 GB | 16.5 GB | Too big | Get file → | |
| Q5_K_S | 14.6 GB | 18.3 GB | Too big | Get file → | |
| Q5_K_M | 15.0 GB | 18.7 GB | Too big | Get file → | |
| Q6_K | 17.4 GB | 21.1 GB | Too big | Get file → |
What GPU do you need for Fusion 7B Quintessence 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: the best quant that fits is IQ3_XXS (8.2 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (12.1 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (17.4 GB file, about 21.1 GB in use).
Which Fusion 7B Quintessence i1 quant should you choose?
Q4_K_M is the usual starting point for Fusion 7B Quintessence i1: it balances file size and quality well. Here it is a 12.7 GB file.
If memory is tight, the smallest file is IQ1_S at 4.6 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 Fusion 7B Quintessence i1
How much VRAM does Fusion 7B Quintessence i1 need?
About 16.5 GB at Q4_K_M with an 8K context window. That is the 12.7 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 Fusion 7B Quintessence i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Fusion 7B Quintessence i1 GGUF?
It depends on the quant: IQ1_S is 4.6 GB, IQ1_M is 5.0 GB, IQ2_XXS is 5.7 GB, IQ2_XS is 6.3 GB, IQ2_S is 6.6 GB, IQ2_M is 7.2 GB and 15 more.
What context length does Fusion 7B Quintessence 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 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download Fusion 7B Quintessence i1 GGUF?
The files are on Hugging Face in the mradermacher/Fusion-7B-Quintessence-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.