QU

quartz micro preview v2

QuartzGGUF by VertexAGIUpdated 2026-10-24
Download on Hugging Face
Parameters100M
Context1K
Layers12
Architecturellama
Smallest quant0.1 GB
Quick answer

quartz micro preview v2 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).

Quartz Micro Preview V2 – a 100M‑parameter Llama‑style chat model

Quartz Micro Preview V2 is a 100.09M‑parameter dense Llama‑architecture decoder trained from scratch on a single GTX 1660 Ti. It is instruction‑tuned for chat but is best suited for short, fluent text generation. The model often states incorrect facts with confidence and struggles with math, reasoning, and code.

Good at

  • Short, fluent text generation
  • Instruction‑tuned chat
  • Research / hobby use

Limits

  • Limited to 1,024 context tokens
  • Weak at math, reasoning, and code
  • Can repeat itself and state wrong facts

Best for

  • Generating quick responses
  • Testing small LLMs
  • Educational demos

Who it’s for. Developers and researchers who need a lightweight, open‑source LLM for experimentation or hobby projects. The model is not suitable for production or critical applications.

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, the Q4_K_M quant (0.07 GB) is ideal, using about 0.7 GB memory at 8 k context. If more precision is needed and 8 GB is available, Q8_0 (0.11 GB) also fits. The F16 quant (0.2 GB) requires more memory and is less efficient.

What GPU do you need for quartz micro preview v2?

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 v2 quant should you choose?

Q4_K_M is the usual starting point for quartz micro preview v2: 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)889
Last updated2026-10-24

Frequently asked questions about quartz micro preview v2

How much VRAM does quartz micro preview v2 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 v2 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 v2 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 v2 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 v2 GGUF?

The files are on Hugging Face in the VertexAGI/quartz-micro-preview-v2 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 v2 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 V2 on 8 GB VRAM?

Yes. The Q4_K_M quant uses 0.7 GB memory at 8 k context, well within an 8 GB GPU.

What is the context length of this model?

The model supports 1,024 tokens of context.

Is the model licensed for commercial use?

It is released under the Apache‑2.0 license, allowing commercial use.

Similar models

Browse all →

More from VertexAGI

All by VertexAGI →

More Quartz models

All Quartz →

Other tiny models

All tiny models →