Lumen 1 Quasar Base needs about 63.7 GB of memory at MXFP4 (a 56.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
Lumen 1 Quasar Base is a 99.5B-parameter Lumen model in GGUF format, quantized by DFveloper. Its trained context length is 256K tokens. The repository has 1 quant file, from 56.4 GB (MXFP4) to 56.4 GB (MXFP4).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 56.4 GB (6 parts) | 63.7 GB | Too big | Get file → |
What GPU do you need for Lumen 1 Quasar Base?
These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Lumen 1 Quasar Base quant should you choose?
MXFP4 (56.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Lumen 1 Quasar Base
How much VRAM does Lumen 1 Quasar Base need?
About 63.7 GB at MXFP4 with an 8K context window. That is the 56.4 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 Lumen 1 Quasar Base on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 63.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Lumen 1 Quasar Base GGUF?
It depends on the quant: MXFP4 is 56.4 GB.
What context length does Lumen 1 Quasar Base support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Lumen 1 Quasar Base GGUF?
The files are on Hugging Face in the DFveloper/Lumen-1-Quasar-Base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.