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 24 quants, from 0.2 GB to 84.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Solar Open 100B – a 103‑billion‑parameter MoE LLM in GGUF format
Solar Open 100B is a 103‑billion‑parameter Mixture‑of‑Experts model based on the glm4moe architecture. It was trained from scratch on 19.7 trillion tokens and supports a 128k context length. The model is available in multiple GGUF quantizations.
Good at
- Large‑scale reasoning
- Instruction following
- Agentic capabilities
Limits
- Requires high VRAM for full precision
- No vision support
- License is Upstage Solar License
Best for
- Enterprise‑grade reasoning tasks
- Complex instruction following
- Agentic workflow automation
Who it’s for. Developers and researchers needing a large MoE model for advanced natural language tasks. The model is suitable for those who can meet the hardware and licensing requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 2.4 GB | Fits | Get file → | |
| IQ1_S | 21.1 GB | 23.2 GB | Too big | Get file → | |
| IQ1_M | 23.4 GB | 25.5 GB | Too big | Get file → | |
| IQ2_XXS | 27.2 GB | 29.3 GB | Too big | Get file → | |
| IQ2_XS | 30.3 GB | 32.4 GB | Too big | Get file → | |
| IQ2_S | 30.8 GB | 32.9 GB | Too big | Get file → | |
| IQ2_M | 33.8 GB | 35.9 GB | Too big | Get file → | |
| Q2_K_S | 35.2 GB | 37.3 GB | Too big | Get file → | |
| Q2_K | 37.7 GB | 39.8 GB | Too big | Get file → | |
| IQ3_XXS | 39.7 GB | 41.8 GB | Too big | Get file → | |
| IQ3_XS | 42.2 GB | 44.3 GB | Too big | Get file → | |
| Q3_K_S | 44.5 GB | 46.6 GB | Too big | Get file → | |
| IQ3_S | 44.5 GB | 46.7 GB | Too big | Get file → | |
| IQ3_M | 45.3 GB | 47.4 GB | Too big | Get file → | |
| Q3_K_M | 49.3 GB | 51.4 GB | Too big | Get file → | |
| Q3_K_L | 53.4 GB | 55.5 GB | Too big | Get file → | |
| IQ4_XS | 54.9 GB | 57.0 GB | Too big | Get file → | |
| Q4_0 | 58.3 GB | 60.4 GB | Too big | Get file → | |
| Q4_K_S | 58.6 GB | 60.7 GB | Too big | Get file → | |
| Q4_K_M | 62.3 GB | 64.4 GB | Too big | Get file → | |
| Q4_1 | 64.4 GB | 66.5 GB | Too big | Get file → | |
| Q5_K_S | 70.8 GB | 72.9 GB | Too big | Get file → | |
| Q5_K_M | 72.9 GB | 75.1 GB | Too big | Get file → | |
| Q6_K | 84.3 GB | 86.4 GB | Too big | Get file → |
For 8 GB VRAM use the IQ1_S quant (21.1 GB file, 23.2 GB memory at 8k context). For 16 GB VRAM use IQ2_S (30.26 GB file, 32.4 GB memory). For 24 GB VRAM use Q3_K_S (44.52 GB file, 46.6 GB memory).
What GPU do you need for 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: the best quant that fits is the main file (0.2 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.4 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.4 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.4 GB in use).
- 24 GB VRAM: the best quant that fits is IQ1_S (21.1 GB file, about 23.2 GB in use).
- 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 IQ3_M (45.3 GB file, about 47.4 GB in use).
Which Solar Open 100B quant should you choose?
Q4_K_M is the usual starting point for Solar Open 100B: it balances file size and quality well. Here it is a 62.3 GB file.
If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Solar Open 100B
How much VRAM does 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 Solar Open 100B on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Solar Open 100B GGUF?
It depends on the quant: file is 0.2 GB, IQ1_S is 21.1 GB, IQ1_M is 23.4 GB, IQ2_XXS is 27.2 GB, IQ2_XS is 30.3 GB, IQ2_S is 30.8 GB and 18 more.
What context length does 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 Solar Open 100B GGUF?
The files are on Hugging Face in the mradermacher/Solar-Open-100B-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 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.
Can I run Solar Open 100B on 8 GB VRAM?
Use the IQ1_S quant; it requires about 23.2 GB memory at 8k context, which is beyond 8 GB VRAM, so it is not feasible.
Does Solar Open 100B support vision tasks?
No, the model has no vision capabilities.
What license applies to the GGUF weights?
The GGUF weights are licensed under the Upstage Solar License.