Parisienne 78B Instruct i1 needs about 38.5 GB of memory at IQ3_XS (a 35.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 19 quants, from 24.3 GB (IQ1_S) to 49.0 GB (Q4_1). Longer context needs more: at 32K tokens the KV cache alone adds about 11.5 GB.
Parisienne 78B Instruct i1 is a 78B-parameter Parisienne model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 19 quant files, from 24.3 GB (IQ1_S) to 49.0 GB (Q4_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 24.3 GB | 27.7 GB | Too big | Get file → | |
| IQ1_M | 25.4 GB | 28.8 GB | Too big | Get file → | |
| IQ2_XXS | 27.3 GB | 30.7 GB | Too big | Get file → | |
| IQ2_XS | 29.0 GB | 32.4 GB | Too big | Get file → | |
| IQ2_S | 29.9 GB | 33.3 GB | Too big | Get file → | |
| IQ2_M | 31.4 GB | 34.8 GB | Too big | Get file → | |
| Q2_K_S | 31.6 GB | 34.9 GB | Too big | Get file → | |
| Q2_K | 31.8 GB | 35.2 GB | Too big | Get file → | |
| IQ3_XXS | 34.0 GB | 37.4 GB | Too big | Get file → | |
| IQ3_XS | 35.1 GB | 38.5 GB | Too big | Get file → | |
| Q3_K_S | 36.8 GB | 40.2 GB | Too big | Get file → | |
| IQ3_S | 36.9 GB | 40.2 GB | Too big | Get file → | |
| IQ3_M | 37.9 GB | 41.3 GB | Too big | Get file → | |
| Q3_K_M | 40.3 GB | 43.7 GB | Too big | Get file → | |
| Q3_K_L | 42.3 GB | 45.7 GB | Too big | Get file → | |
| IQ4_XS | 42.6 GB | 45.9 GB | Too big | Get file → | |
| Q4_0 | 44.3 GB | 47.7 GB | Too big | Get file → | |
| Q4_K_S | 46.9 GB | 50.3 GB | Too big | Get file → | |
| Q4_1 | 49.0 GB | 52.4 GB | Too big | Get file → |
What GPU do you need for Parisienne 78B Instruct 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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is IQ2_XXS (27.3 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_0 (44.3 GB file, about 47.7 GB in use).
Which Parisienne 78B Instruct i1 quant should you choose?
IQ3_XS (35.1 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 IQ1_S at 24.3 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
Frequently asked questions about Parisienne 78B Instruct i1
How much VRAM does Parisienne 78B Instruct i1 need?
About 38.5 GB at IQ3_XS with an 8K context window. That is the 35.1 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 Parisienne 78B Instruct i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Parisienne 78B Instruct i1 GGUF?
It depends on the quant: IQ1_S is 24.3 GB, IQ1_M is 25.4 GB, IQ2_XXS is 27.3 GB, IQ2_XS is 29.0 GB, IQ2_S is 29.9 GB, IQ2_M is 31.4 GB and 13 more.
What context length does Parisienne 78B Instruct 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 2.9 GB at 8K and 11.5 GB at 32K.
Where can I download Parisienne 78B Instruct i1 GGUF?
The files are on Hugging Face in the mradermacher/Parisienne-78B-Instruct-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.