upstage.Solar Open 100B needs about 64.4 GB of memory at Q4_K_M (a 62.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 27.2 GB (IQ2_XXS) to 109.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
upstage.Solar Open 100B is a 103B-parameter Solar model in GGUF format, quantized by DevQuasar-11. Its trained context length is 128K tokens. The repository has 7 quant files, from 27.2 GB (IQ2_XXS) to 109.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 27.2 GB | 29.3 GB | Too big | Get file → | |
| Q2_K | 37.7 GB | 39.8 GB | Too big | Get file → | |
| Q3_K_M | 49.3 GB (4 parts) | 51.4 GB | Too big | Get file → | |
| Q4_K_M | 62.3 GB (4 parts) | 64.4 GB | Too big | Get file → | |
| Q5_K_M | 72.9 GB (5 parts) | 75.1 GB | Too big | Get file → | |
| Q6_K | 84.3 GB (6 parts) | 86.4 GB | Too big | Get file → | |
| Q8_0 | 109.2 GB (7 parts) | 111.3 GB | Too big | Get file → |
What GPU do you need for upstage.Solar Open 100B?
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 (27.2 GB file, about 29.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q2_K (37.7 GB file, about 39.8 GB in use).
Which upstage.Solar Open 100B quant should you choose?
Q4_K_M is the usual starting point for upstage.Solar Open 100B: it balances file size and quality well. Here it is a 62.3 GB file.
The Q8_0 file is 109.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ2_XXS at 27.2 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 upstage.Solar Open 100B
How much VRAM does upstage.Solar Open 100B need?
About 64.4 GB at Q4_K_M with an 8K context window. That is the 62.3 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 upstage.Solar Open 100B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of upstage.Solar Open 100B GGUF?
It depends on the quant: IQ2_XXS is 27.2 GB, Q2_K is 37.7 GB, Q3_K_M is 49.3 GB, Q4_K_M is 62.3 GB, Q5_K_M is 72.9 GB, Q6_K is 84.3 GB and 1 more.
What context length does upstage.Solar Open 100B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download upstage.Solar Open 100B GGUF?
The files are on Hugging Face in the DevQuasar-11/upstage.Solar-Open-100B-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 upstage.Solar Open 100B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.