LL

Llama3.2 ColdBrew 4x3B Argon Test1

LlamaGGUF by TherosUpdated 2025-10-19
Download on Hugging Face
Parameters9.55B
Context128K
Layers28
Architecturellama
Smallest quant6.8 GB
Quick answer

Llama3.2 ColdBrew 4x3B Argon Test1 needs about 8.3 GB of memory at Q5_K_M (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama3.2 ColdBrew 4x3B Argon Test1 is a 9.55B-parameter Llama model in GGUF format, quantized by Theros. Its trained context length is 128K tokens. The repository has 1 quant file, from 6.8 GB (Q5_K_M) to 6.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M6.8 GB 8.3 GB
Too big Get file →

What GPU do you need for Llama3.2 ColdBrew 4x3B Argon Test1?

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: the best quant that fits is Q5_K_M (6.8 GB file, about 8.3 GB in use).

Which Llama3.2 ColdBrew 4x3B Argon Test1 quant should you choose?

Q5_K_M (6.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters9.55B (approximate, mixture of experts)
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byTheros
FamilyLlama
Downloads (HF)17
Last updated2025-10-19

Frequently asked questions about Llama3.2 ColdBrew 4x3B Argon Test1

How much VRAM does Llama3.2 ColdBrew 4x3B Argon Test1 need?

About 8.3 GB at Q5_K_M with an 8K context window. That is the 6.8 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 Llama3.2 ColdBrew 4x3B Argon Test1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama3.2 ColdBrew 4x3B Argon Test1 GGUF?

It depends on the quant: Q5_K_M is 6.8 GB.

What context length does Llama3.2 ColdBrew 4x3B Argon Test1 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 Llama3.2 ColdBrew 4x3B Argon Test1 GGUF?

The files are on Hugging Face in the Theros/Llama3.2-ColdBrew-4x3B-Argon-test1-Q5_K_M-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 Llama3.2 ColdBrew 4x3B Argon Test1 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Theros

All by Theros →

More Llama models

All Llama →

Other medium models

All medium models →