TH

ThinkerLlama 3B Q4 0

ThinkerllamaGGUF by matrixportalxUpdated 2024-12-31
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant1.9 GB
Quick answer

ThinkerLlama 3B Q4 0 needs about 3.4 GB of memory at Q4_0 (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

ThinkerLlama 3B Q4 0 is a 3.21B-parameter Thinkerllama model in GGUF format, quantized by matrixportalx. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.9 GB (Q4_0) to 1.9 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.9 GB 3.4 GB
Fits Get file →

What GPU do you need for ThinkerLlama 3B Q4 0?

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 Q4_0 (1.9 GB file, about 3.4 GB in use).

Which ThinkerLlama 3B Q4 0 quant should you choose?

Q4_0 (1.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 bymatrixportalx
Downloads (HF)28
Last updated2024-12-31

Frequently asked questions about ThinkerLlama 3B Q4 0

How much VRAM does ThinkerLlama 3B Q4 0 need?

About 3.4 GB at Q4_0 with an 8K context window. That is the 1.9 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 ThinkerLlama 3B Q4 0 on an 8 GB GPU?

Yes, with Q4_0: the 1.9 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ThinkerLlama 3B Q4 0 GGUF?

It depends on the quant: Q4_0 is 1.9 GB.

What context length does ThinkerLlama 3B Q4 0 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 ThinkerLlama 3B Q4 0 GGUF?

The files are on Hugging Face in the matrixportalx/ThinkerLlama-3B-Q4_0-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 ThinkerLlama-3B

Similar models

Browse all →

More from matrixportalx

All by matrixportalx →

More Thinkerllama models

All Thinkerllama →

Other tiny models

All tiny models →