LL

Schematron-3B

LlamaGGUF by MungertUpdated 2026-02-15
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant0.0 GB
Quick answer

Schematron-3B 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 37 quants, from 0.0 GB to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Schematron-3B: Llama‑3.2‑based model for structured HTML extraction

Schematron-3B is a 3.21B‑parameter Llama model fine‑tuned for converting noisy HTML into typed JSON. It supports tools and has a 131072‑token context window. The model is released under the llama3.2 license.

Good at

  • HTML to JSON conversion
  • Schema‑first data extraction
  • Long‑context processing

Limits

  • No vision support
  • Requires 8k context for estimates
  • License restricts commercial use

Best for

  • Web scraping pipelines
  • Data ingestion workflows
  • Structured record generation

Who it’s for. Developers building web‑scraping or data‑ingestion systems that need clean, schema‑conformant JSON. The model is suitable for applications that can run llama.cpp and manage the required VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
Q2_K_S1.4 GB 2.9 GB
Fits Get file →
IQ3_XXS1.5 GB 2.9 GB
Fits Get file →
Q2_K_M1.5 GB 2.9 GB
Fits Get file →
IQ2_XS1.5 GB 3.0 GB
Fits Get file →
IQ3_XS1.5 GB 3.0 GB
Fits Get file →
IQ2_S1.6 GB 3.0 GB
Fits Get file →
IQ2_M1.6 GB 3.0 GB
Fits Get file →
Q2_K_L1.6 GB 3.0 GB
Fits Get file →
IQ3_M1.6 GB 3.0 GB
Fits Get file →
IQ3_S1.6 GB 3.0 GB
Fits Get file →
Q3_K_S1.8 GB 3.2 GB
Fits Get file →
Q3_K_M1.8 GB 3.3 GB
Fits Get file →
Q4_01.8 GB 3.3 GB
Fits Get file →
IQ4_XS1.8 GB 3.3 GB
Fits Get file →
Q3_K_L1.9 GB 3.3 GB
Fits Get file →
IQ4_NL1.9 GB 3.4 GB
Fits Get file →
Q4_K_S2.0 GB 3.4 GB
Fits Get file →
Q4_02.0 GB 3.5 GB
Fits Get file →
Q4_12.0 GB 3.5 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q4_K_L2.1 GB 3.6 GB
Fits Get file →
Q4_12.2 GB 3.6 GB
Fits Get file →
Q5_02.2 GB 3.7 GB
Fits Get file →
Q5_K_S2.3 GB 3.8 GB
Fits Get file →
Q5_02.4 GB 3.8 GB
Fits Get file →
Q5_K_M2.4 GB 3.8 GB
Fits Get file →
Q5_12.4 GB 3.9 GB
Fits Get file →
Q5_K_L2.5 GB 3.9 GB
Fits Get file →
Q5_12.5 GB 4.0 GB
Fits Get file →
Q6_K_M2.6 GB 4.1 GB
Fits Get file →
Q6_K_L2.7 GB 4.2 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
BF164.8 GB 6.2 GB
Fits Get file →
F164.8 GB 6.2 GB
Fits Get file →
BF166.4 GB 7.9 GB
Tight Get file →
F166.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q2_K_S (1.45 GB, 2.9 GB memory) or Q3_K_S (1.76 GB, 3.2 GB memory). If 12 GB VRAM is available, Q4_K_M (2.04 GB, 3.5 GB memory) or Q5_K_M (2.37 GB, 3.8 GB memory) provide higher precision. Larger models like Q8_0 (3.42 GB, 4.9 GB memory) need 16 GB or more.

What GPU do you need for Schematron-3B?

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_1 (2.5 GB file, about 4.0 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 BF16 (6.4 GB file, about 7.9 GB in use).

Which Schematron-3B quant should you choose?

Q4_K_M is the usual starting point for Schematron-3B: 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

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 byMungert
FamilyLlama
Licensellama3.2
Downloads (HF)820
Last updated2026-02-15

Frequently asked questions about Schematron-3B

How much VRAM does Schematron-3B 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 Schematron-3B on an 8 GB GPU?

Yes, with BF16: 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 Schematron-3B GGUF?

It depends on the quant: file is 0.0 GB, Q2_K_S is 1.4 GB, IQ3_XXS is 1.5 GB, Q2_K_M is 1.5 GB, IQ2_XS is 1.5 GB, IQ3_XS is 1.5 GB and 31 more.

What context length does Schematron-3B 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 Schematron-3B GGUF?

The files are on Hugging Face in the Mungert/Schematron-3B-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 Schematron-3B use?

Hugging Face lists the license as llama3.2. 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 Schematron-3B on 8 GB VRAM?

Yes, using Q2_K_S or Q3_K_S quantizations will fit within 8 GB VRAM with approximate 2.9–3.2 GB memory usage.

Does Schematron-3B support image input?

No, the model does not have vision capabilities and only processes text.

What license applies to Schematron-3B?

The model is released under the llama3.2 license, which has specific usage restrictions.

Other GGUFs of Llama-3.2-3B-Instruct

Similar models

Browse all →

More from Mungert

All by Mungert →

More Llama models

All Llama →

Other tiny models

All tiny models →