MI

MIST Extract 1.0

MistGGUF by mradermacherUpdated 2026-10-15
Download on Hugging Face
Parameters4.21B
Context256K
Layers33
Architectureqwen35
Smallest quant1.9 GB
Quick answer

MIST Extract 1.0 needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.9 GB (Q2_K) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

MIST Extract 1.0 – 4.21B Qwen35 model for document extraction with vision support

MIST Extract 1.0 is a 4.21B Qwen35 model that turns documents into JSON. It supports vision, extracting fields from text, photos, or scans, and provides calibrated confidence for each field. The model is trained on English and African languages.

Good at

  • Document to JSON conversion
  • Calibrated confidence per field
  • Vision-based extraction from photos

Limits

  • No vision beyond document images
  • Large context 262144 tokens
  • License apache-2.0

Best for

  • Mobile money receipt extraction
  • Bank statement parsing
  • Multi-language form filling

Who it’s for. Developers building document automation for African businesses and multilingual contexts. Suitable for applications needing accurate field extraction and confidence scores.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 3.5 GB
Fits Get file →
Q3_K_S2.1 GB 3.7 GB
Fits Get file →
Q3_K_M2.3 GB 3.9 GB
Fits Get file →
Q3_K_L2.4 GB 4.0 GB
Fits Get file →
IQ4_XS2.5 GB 4.1 GB
Fits Get file →
Q4_K_S2.6 GB 4.2 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_S3.0 GB 4.6 GB
Fits Get file →
Q5_K_M3.1 GB 4.7 GB
Fits Get file →
Q6_K3.5 GB 5.1 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
F168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.71 GB file, ~4.3 GB memory) or Q5_K_M (3.07 GB file, ~4.7 GB memory). For 12 GB VRAM, Q6_K (3.46 GB file, ~5.1 GB memory) is a good choice. For 16 GB VRAM, Q8_0 (4.48 GB file, ~6.1 GB memory) provides higher quality.

What GPU do you need for MIST Extract 1.0?

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 Q3_K_L (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.4 GB file, about 10.0 GB in use).

Which MIST Extract 1.0 quant should you choose?

Q4_K_M is the usual starting point for MIST Extract 1.0: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.5 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 1.9 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

Architectureqwen35
Parameters4.21B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bymradermacher
FamilyMist
Licenseapache-2.0
Downloads (HF)630
Last updated2026-10-15

Frequently asked questions about MIST Extract 1.0

How much VRAM does MIST Extract 1.0 need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 MIST Extract 1.0 on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MIST Extract 1.0 GGUF?

It depends on the quant: Q2_K is 1.9 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, IQ4_XS is 2.5 GB, Q4_K_S is 2.6 GB and 6 more.

What context length does MIST Extract 1.0 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download MIST Extract 1.0 GGUF?

The files are on Hugging Face in the mradermacher/MIST-Extract-1.0-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 MIST Extract 1.0 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 MIST Extract on 8 GB VRAM?

Yes, the Q4_K_M or Q5_K_M quant files fit within 8 GB VRAM, using approximately 4.3–4.7 GB of memory at 8 k context.

Does it support African languages?

Yes, it is trained for English and African-language documents and performs well on African languages.

What is the context length?

The model supports a context length of 262144 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mist models

All Mist →

Other small models

All small models →