SI

silx-ai/Quasar-10B

SilxGGUF by SakaiSecUpdated 2026-03-18
Download on Hugging Face
Parameters8.6B
Context2048K
Layers32
Architectureqwen35
Smallest quant4.5 GB
Quick answer

silx-ai/Quasar-10B needs about 7.0 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 4.5 GB (Q3_K_M) to 17.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

silx-ai/Quasar-10B is a 8.6B-parameter Silx model in GGUF format, quantized by SakaiSec. Its trained context length is 2048K tokens. The repository has 7 quant files, from 4.5 GB (Q3_K_M) to 17.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M4.5 GB 6.0 GB
Fits Get file →
Q4_05.1 GB 6.7 GB
Fits Get file →
Q4_K_M5.4 GB 7.0 GB
Fits Get file →
Q5_06.1 GB 7.6 GB
Tight Get file →
Q5_K_M6.2 GB 7.8 GB
Tight Get file →
Q8_09.2 GB 10.7 GB
Too big Get file →
F1617.2 GB 18.8 GB
Too big Get file →

What GPU do you need for silx-ai/Quasar-10B?

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: the best quant that fits is Q3_K_M (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.2 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.2 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.2 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.2 GB file, about 18.8 GB in use).

Which silx-ai/Quasar-10B quant should you choose?

Q4_K_M is the usual starting point for silx-ai/Quasar-10B: it balances file size and quality well. Here it is a 5.4 GB file.

The Q8_0 file is 9.2 GB, about 1.7 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 Q3_K_M at 4.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.6B
Layers32
Trained context2,097,152 tokens
KV cache (fp16)128 KB per token

Source

Quantized bySakaiSec
FamilySilx
Licenseapache-2.0
Downloads (HF)203
Last updated2026-03-18

Frequently asked questions about silx-ai/Quasar-10B

How much VRAM does silx-ai/Quasar-10B need?

About 7.0 GB at Q4_K_M with an 8K context window. That is the 5.4 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 silx-ai/Quasar-10B on an 8 GB GPU?

Yes, with Q5_K_M: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of silx-ai/Quasar-10B GGUF?

It depends on the quant: Q3_K_M is 4.5 GB, Q4_0 is 5.1 GB, Q4_K_M is 5.4 GB, Q5_0 is 6.1 GB, Q5_K_M is 6.2 GB, Q8_0 is 9.2 GB and 1 more.

What context length does silx-ai/Quasar-10B support?

The GGUF header lists a trained context length of 2,097,152 tokens (2048K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download silx-ai/Quasar-10B GGUF?

The files are on Hugging Face in the SakaiSec/Quasar-10B-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 silx-ai/Quasar-10B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from SakaiSec

All by SakaiSec →

Other small models

All small models →