AS

Ascendant

AscendantGGUF by blascotobascoUpdated 2026-01-22
Download on Hugging Face
Parameters18.4B
Context128K
Layers28
Architecturellama
Smallest quant11.3 GB
Quick answer

Ascendant needs about 12.8 GB of memory at Q4_K_M (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 11.3 GB (Q4_K_M) to 36.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Ascendant is a 18.4B-parameter Ascendant model in GGUF format, quantized by blascotobasco. Its trained context length is 128K tokens. The repository has 2 quant files, from 11.3 GB (Q4_K_M) to 36.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M11.3 GB 12.8 GB
Too big Get file →
F1636.8 GB 38.3 GB
Too big Get file →

What GPU do you need for Ascendant?

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: the best quant that fits is Q4_K_M (11.3 GB file, about 12.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (11.3 GB file, about 12.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (11.3 GB file, about 12.8 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (36.8 GB file, about 38.3 GB in use).

Which Ascendant quant should you choose?

Q4_K_M is the usual starting point for Ascendant: it balances file size and quality well. Here it is a 11.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters18.4B (approximate, mixture of experts)
Active parameters6B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byblascotobasco
FamilyAscendant
Downloads (HF)32
Last updated2026-01-22

Frequently asked questions about Ascendant

How much VRAM does Ascendant need?

About 12.8 GB at Q4_K_M with an 8K context window. That is the 11.3 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 Ascendant on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ascendant GGUF?

It depends on the quant: Q4_K_M is 11.3 GB, F16 is 36.8 GB.

What context length does Ascendant support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Ascendant GGUF?

The files are on Hugging Face in the blascotobasco/L3.2-Ascendant-8E-A6B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of L3.2-Ascendant-8E-A6B

Similar models

Browse all →

More from blascotobasco

All by blascotobasco →

More Ascendant models

All Ascendant →

Other medium models

All medium models →