QU

quartz micro preview v3 base

QuartzGGUF by VertexAGIUpdated 2026-11-02
Download on Hugging Face
Parameters100M
Context1K
Layers12
Architecturellama
Smallest quant0.1 GB
Quick answer

quartz micro preview v3 base needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q4_K_M) to 0.2 GB (F16).

A 100M‑parameter Llama‑style language model

Quartz Micro Preview V3 Base is a 100.09M‑parameter dense Llama‑architecture decoder. It has 12 layers, hidden size 768, 12 heads, 4 KV heads, SwiGLU 2048, RoPE, and a 1,024‑token context window. The model is trained from scratch on a single GTX 1660 Ti.

Good at

  • Short fluent text generation
  • Basic conversational responses
  • Simple text completion

Limits

  • Limited context length of 1,024 tokens
  • Weak at math, reasoning, and code
  • May produce incorrect facts

Best for

  • Rapid prototyping of small language models
  • Embedded devices with low VRAM
  • Educational demonstrations of Llama architecture

Who it’s for. Developers and researchers needing a lightweight Llama‑style model for quick experimentation. It is suitable for environments with limited GPU memory and for learning about model internals.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.2 GB 0.7 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (0.07 GB file, ~0.7 GB memory at 8k context). For 12 GB VRAM use Q8_0 (0.11 GB file, ~0.7 GB memory). For higher precision use F16 (0.2 GB file, ~0.8 GB memory). Estimates are approximate.

What GPU do you need for quartz micro preview v3 base?

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 F16 (0.2 GB file, about 0.8 GB in use).

Which quartz micro preview v3 base quant should you choose?

Q4_K_M is the usual starting point for quartz micro preview v3 base: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.1 GB, about 1.6 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
Parameters100M
Layers12
Trained context1,024 tokens
KV cache (fp16)12 KB per token

Source

Quantized byVertexAGI
FamilyQuartz
Licenseapache-2.0
Downloads (HF)583
Last updated2026-11-02

Frequently asked questions about quartz micro preview v3 base

How much VRAM does quartz micro preview v3 base need?

About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 quartz micro preview v3 base on an 8 GB GPU?

Yes, with F16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of quartz micro preview v3 base GGUF?

It depends on the quant: Q4_K_M is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB.

What context length does quartz micro preview v3 base support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.

Where can I download quartz micro preview v3 base GGUF?

The files are on Hugging Face in the VertexAGI/quartz-micro-preview-v3-base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does quartz micro preview v3 base 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.

Can I run Quartz Micro Preview V3 Base on 8 GB VRAM?

Yes, the Q4_K_M quantized file is 0.07 GB and requires about 0.7 GB of VRAM at 8k context.

Does this model support vision or multimodal input?

No, it is a text‑only language model with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from VertexAGI

All by VertexAGI →

More Quartz models

All Quartz →

Other tiny models

All tiny models →