shqiponja 59b v1 i1 needs about 39.9 GB of memory at Q4_K_M (a 35.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 13.3 GB (IQ1_S) to 48.9 GB (Q6_K).
shqiponja 59b v1 i1 is a 58.9B-parameter Shqiponja model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 21 quant files, from 13.3 GB (IQ1_S) to 48.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 13.3 GB | 15.5 GB | Too big | Get file → | |
| IQ1_M | 14.4 GB | 16.7 GB | Too big | Get file → | |
| IQ2_XXS | 16.4 GB | 18.6 GB | Too big | Get file → | |
| IQ2_XS | 18.1 GB | 20.4 GB | Too big | Get file → | |
| IQ2_S | 19.1 GB | 21.4 GB | Too big | Get file → | |
| IQ2_M | 20.7 GB | 22.9 GB | Too big | Get file → | |
| Q2_K | 22.4 GB | 24.6 GB | Too big | Get file → | |
| IQ3_XXS | 23.3 GB | 25.6 GB | Too big | Get file → | |
| IQ3_XS | 24.8 GB | 27.0 GB | Too big | Get file → | |
| Q3_K_S | 26.1 GB | 28.3 GB | Too big | Get file → | |
| IQ3_S | 26.2 GB | 28.4 GB | Too big | Get file → | |
| IQ3_M | 27.1 GB | 29.4 GB | Too big | Get file → | |
| Q3_K_M | 29.0 GB | 31.2 GB | Too big | Get file → | |
| Q3_K_L | 31.6 GB | 33.8 GB | Too big | Get file → | |
| IQ4_XS | 32.1 GB | 34.4 GB | Too big | Get file → | |
| Q4_0 | 33.9 GB | 36.2 GB | Too big | Get file → | |
| Q4_K_S | 34.1 GB | 36.3 GB | Too big | Get file → | |
| Q4_K_M | 35.9 GB | 38.1 GB | Too big | Get file → | |
| Q5_K_S | 41.1 GB | 43.4 GB | Too big | Get file → | |
| Q5_K_M | 42.2 GB | 44.4 GB | Too big | Get file → | |
| Q6_K | 48.9 GB | 51.1 GB | Too big | Get file → |
What GPU do you need for shqiponja 59b v1 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 IQ2_S (19.1 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_M (27.1 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (42.2 GB file, about 46.2 GB in use).
Which shqiponja 59b v1 i1 quant should you choose?
Q4_K_M is the usual starting point for shqiponja 59b v1 i1: it balances file size and quality well. Here it is a 35.9 GB file.
If memory is tight, the smallest file is IQ1_S at 13.3 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
Source
Frequently asked questions about shqiponja 59b v1 i1
How much VRAM does shqiponja 59b v1 i1 need?
About 39.9 GB at Q4_K_M with an 8K context window. That is the 35.9 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 shqiponja 59b v1 i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of shqiponja 59b v1 i1 GGUF?
It depends on the quant: IQ1_S is 13.3 GB, IQ1_M is 14.4 GB, IQ2_XXS is 16.4 GB, IQ2_XS is 18.1 GB, IQ2_S is 19.1 GB, IQ2_M is 20.7 GB and 15 more.
What context length does shqiponja 59b v1 i1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.5 GB at 8K and 1.7 GB at 4K.
Where can I download shqiponja 59b v1 i1 GGUF?
The files are on Hugging Face in the mradermacher/shqiponja-59b-v1-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 shqiponja 59b v1 i1 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.