CO

L3.2 3B ColdBrew Reflect

ColdbrewGGUF by SvalTekUpdated 2024-10-04
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant2.0 GB
Quick answer

L3.2 3B ColdBrew Reflect needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.0 GB (Q4_K_M) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

L3.2 3B ColdBrew Reflect is a 3.21B-parameter Coldbrew model in GGUF format, quantized by SvalTek. Its trained context length is 128K tokens. The repository has 4 quant files, from 2.0 GB (Q4_K_M) to 6.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q5_K_M2.3 GB 3.8 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
F166.4 GB 7.9 GB
Tight Get file →

What GPU do you need for L3.2 3B ColdBrew Reflect?

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 Q5_K_M (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 GB in use).

Which L3.2 3B ColdBrew Reflect quant should you choose?

Q4_K_M is the usual starting point for L3.2 3B ColdBrew Reflect: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.4 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
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bySvalTek
FamilyColdbrew
Licenseapache-2.0
Downloads (HF)23
Last updated2024-10-04

Frequently asked questions about L3.2 3B ColdBrew Reflect

How much VRAM does L3.2 3B ColdBrew Reflect need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 3B ColdBrew Reflect on an 8 GB GPU?

Yes, with F16: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of L3.2 3B ColdBrew Reflect GGUF?

It depends on the quant: Q4_K_M is 2.0 GB, Q5_K_M is 2.3 GB, Q8_0 is 3.4 GB, F16 is 6.4 GB.

What context length does L3.2 3B ColdBrew Reflect 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 3B ColdBrew Reflect GGUF?

The files are on Hugging Face in the SvalTek/L3.2-3B-ColdBrew-Reflect-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 L3.2 3B ColdBrew Reflect 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.

Other GGUFs of L3.2-3B-ColdBrew-Reflect

Similar models

Browse all →

More from SvalTek

All by SvalTek →

More Coldbrew models

All Coldbrew →

Other tiny models

All tiny models →