FI

FireRed OCR

FireredGGUF by mradermacherUpdated 2026-10-21
Download on Hugging Face
Parameters1.72B
Context256K
Layers28
Architectureqwen3vl
Smallest quant0.8 GB
Quick answer

FireRed OCR needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.8 GB (Q2_K) to 3.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

FireRed OCR – a 1.72B Qwen3VL model for precise document parsing

FireRed OCR is a 1.72B parameter Qwen3VL model fine‑tuned for end‑to‑end document OCR. It supports vision and tools and runs in GGUF format. The model is licensed under Apache‑2.0.

Good at

  • High‑accuracy OCR on structured documents
  • Vision‑language reasoning
  • Tool‑based interactions

Limits

  • No vision support in some quant variants
  • Requires 8k context for estimates
  • Large VRAM needed for full precision

Best for

  • OCR of complex forms
  • Table extraction
  • PDF to Markdown conversion

Who it’s for. Developers needing a lightweight OCR model for structured documents. The model is suitable for integration into pipelines that require accurate layout parsing and text extraction.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 GB 2.2 GB
Fits Get file →
Q3_K_S0.9 GB 2.3 GB
Fits Get file →
Q3_K_M0.9 GB 2.4 GB
Fits Get file →
Q3_K_L1.0 GB 2.4 GB
Fits Get file →
IQ4_XS1.0 GB 2.5 GB
Fits Get file →
Q4_K_S1.1 GB 2.5 GB
Fits Get file →
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
Q5_K_S1.2 GB 2.7 GB
Fits Get file →
Q5_K_M1.3 GB 2.7 GB
Fits Get file →
Q6_K1.4 GB 2.9 GB
Fits Get file →
Q8_01.8 GB 3.3 GB
Fits Get file →
F163.4 GB 4.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.11 GB, estimated 2.5 GB memory). If memory is tighter, Q3_K_S (0.87 GB, 2.3 GB memory) is a good compromise. For the best accuracy with 12 GB VRAM, choose F16 (3.45 GB, 4.9 GB memory).

What GPU do you need for FireRed OCR?

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 Q8_0 (1.8 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).

Which FireRed OCR quant should you choose?

Q4_K_M is the usual starting point for FireRed OCR: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 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 Q2_K at 0.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vl
Parameters1.72B
Layers28
Trained context262,144 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyFirered
Licenseapache-2.0
Downloads (HF)647
Last updated2026-10-21

Frequently asked questions about FireRed OCR

How much VRAM does FireRed OCR need?

About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 FireRed OCR on an 8 GB GPU?

Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FireRed OCR GGUF?

It depends on the quant: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB, Q4_K_S is 1.1 GB and 6 more.

What context length does FireRed OCR support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 FireRed OCR GGUF?

The files are on Hugging Face in the mradermacher/FireRed-OCR-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 FireRed OCR 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 FireRed OCR on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 2.5 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

Yes, FireRed OCR has vision capability as part of its detected abilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of FireRed-OCR

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Firered models

All Firered →

Other tiny models

All tiny models →