LL

Superthoughts lite v2 MOE Llama3.2

LlamaGGUF by PinkstackUpdated 2025-05-11
Download on Hugging Face
Parameters3.91B
Context128K
Layers16
Architecturellama
Smallest quant2.4 GB
Quick answer

Superthoughts lite v2 MOE Llama3.2 needs about 3.2 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 2.4 GB (Q4_K_M) to 4.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

Superthoughts lite v2 MOE Llama3.2 is a 3.91B-parameter Llama model in GGUF format, quantized by Pinkstack. Its trained context length is 128K tokens. The repository has 3 quant files, from 2.4 GB (Q4_K_M) to 4.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.4 GB 3.2 GB
Fits Get file →
Q6_K3.2 GB 4.0 GB
Fits Get file →
Q8_04.2 GB 4.9 GB
Fits Get file →

What GPU do you need for Superthoughts lite v2 MOE Llama3.2?

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 Q6_K (3.2 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 4.9 GB in use).

Which Superthoughts lite v2 MOE Llama3.2 quant should you choose?

Q4_K_M is the usual starting point for Superthoughts lite v2 MOE Llama3.2: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.91B (approximate, mixture of experts)
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized byPinkstack
FamilyLlama
Licensellama3.2
Downloads (HF)199
Last updated2025-05-11

Frequently asked questions about Superthoughts lite v2 MOE Llama3.2

How much VRAM does Superthoughts lite v2 MOE Llama3.2 need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Superthoughts lite v2 MOE Llama3.2 on an 8 GB GPU?

Yes, with Q8_0: the 4.2 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Superthoughts lite v2 MOE Llama3.2 GGUF?

It depends on the quant: Q4_K_M is 2.4 GB, Q6_K is 3.2 GB, Q8_0 is 4.2 GB.

What context length does Superthoughts lite v2 MOE Llama3.2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download Superthoughts lite v2 MOE Llama3.2 GGUF?

The files are on Hugging Face in the Pinkstack/Superthoughts-lite-v2-MOE-Llama3.2-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 Superthoughts lite v2 MOE Llama3.2 use?

Hugging Face lists the license as llama3.2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Superthoughts-lite-v2-MOE-Llama3.2

Similar models

Browse all →

More from Pinkstack

All by Pinkstack →

More Llama models

All Llama →

Other small models

All small models →