AS

L3.2 Ascendant Prime 16E A6B

AscendantGGUF by mradermacherUpdated 2026-01-24
Download on Hugging Face
Parameters34.9B
Context128K
Layers28
Architecturellama
Smallest quant0.0 GB
Quick answer

L3.2 Ascendant Prime 16E A6B needs about 22.7 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 28.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

34.9B parameter Llama 3.2 model with Mixture of Experts and tools support

L3.2 Ascendant Prime 16E A6B is a 34.9B parameter Llama 3.2 model that incorporates a mixture of experts. It was trained with a context length of 131072 tokens and supports tool usage. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Mixture of experts
  • Tool integration

Limits

  • No vision support
  • License not specified
  • Large VRAM requirement

Best for

  • Long‑form content generation
  • Complex tool‑based workflows
  • Research prototyping

Who it’s for. Developers and researchers who need a high‑capacity Llama 3.2 model for text‑only tasks and tool integration. The model is suitable for those who can allocate sufficient GPU memory for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.5 GB
Fits Get file →
IQ1_S7.2 GB 8.7 GB
Too big Get file →
IQ1_M8.0 GB 9.5 GB
Too big Get file →
IQ2_XXS9.3 GB 10.7 GB
Too big Get file →
IQ2_XS10.3 GB 11.8 GB
Too big Get file →
IQ2_S10.5 GB 11.9 GB
Too big Get file →
IQ2_M11.5 GB 13.0 GB
Too big Get file →
Q2_K_S11.9 GB 13.4 GB
Too big Get file →
Q2_K12.8 GB 14.3 GB
Too big Get file →
IQ3_XXS13.5 GB 14.9 GB
Too big Get file →
IQ3_XS14.4 GB 15.8 GB
Too big Get file →
IQ3_S15.2 GB 16.6 GB
Too big Get file →
Q3_K_S15.2 GB 16.6 GB
Too big Get file →
IQ3_M15.4 GB 16.8 GB
Too big Get file →
Q3_K_M16.8 GB 18.2 GB
Too big Get file →
Q3_K_L18.2 GB 19.6 GB
Too big Get file →
IQ4_XS18.7 GB 20.1 GB
Too big Get file →
Q4_019.8 GB 21.3 GB
Too big Get file →
Q4_K_S19.9 GB 21.4 GB
Too big Get file →
Q4_K_M21.2 GB 22.7 GB
Too big Get file →
Q4_121.9 GB 23.4 GB
Too big Get file →
Q5_K_S24.1 GB 25.5 GB
Too big Get file →
Q5_K_M24.8 GB 26.3 GB
Too big Get file →
Q6_K28.7 GB 30.1 GB
Too big Get file →

For 8‑GB VRAM, the smallest quant that fits is IQ1_S (8.7 GB memory estimate). If you have 12‑GB VRAM, IQ2_XS (11.8 GB) or Q2_K (14.3 GB) are options. For 16‑GB VRAM, IQ3_S (16.6 GB) or Q3_K_M (18.2 GB) provide higher quality. Estimates are approximate.

What GPU do you need for L3.2 Ascendant Prime 16E A6B?

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 (0.0 GB file, about 1.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (10.5 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (14.4 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.9 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.7 GB file, about 30.1 GB in use).

Which L3.2 Ascendant Prime 16E A6B quant should you choose?

Q4_K_M is the usual starting point for L3.2 Ascendant Prime 16E A6B: it balances file size and quality well. Here it is a 21.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architecturellama
Parameters34.9B (approximate, mixture of experts)
Active parameters6B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyAscendant
Downloads (HF)840
Last updated2026-01-24

Frequently asked questions about L3.2 Ascendant Prime 16E A6B

How much VRAM does L3.2 Ascendant Prime 16E A6B need?

About 22.7 GB at Q4_K_M with an 8K context window. That is the 21.2 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 L3.2 Ascendant Prime 16E A6B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of L3.2 Ascendant Prime 16E A6B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.2 GB, IQ1_M is 8.0 GB, IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, IQ2_S is 10.5 GB and 18 more.

What context length does L3.2 Ascendant Prime 16E A6B 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 L3.2 Ascendant Prime 16E A6B GGUF?

The files are on Hugging Face in the mradermacher/L3.2-Ascendant-Prime-16E-A6B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

The smallest quant that fits 8 GB VRAM is IQ1_S, which requires 8.7 GB memory at 8k context. It will not fit within 8 GB VRAM.

How many parameters does this model have?

The model contains 34.9 B parameters, with 6 B active parameters in the mixture of experts.

Does this model support vision?

No, the model does not have vision capabilities.

Other GGUFs of L3.2-Ascendant-Prime-16E-A6B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ascendant models

All Ascendant →

Other large models

All large models →