MI

Mizan v2 4B

MizanGGUF by mradermacherUpdated 2026-10-14
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant1.9 GB
Quick answer

Mizan v2 4B 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 4.3 GB.

Mizan v2 4B – Persian‑first decision model with text and image support

Mizan v2 4B is a 4.21B parameter model built on the qwen35 architecture. It evaluates text and images in a single forward pass, returning calibrated probabilities without generating text. The model is released under Apache‑2.0 and is compatible with llama.cpp b11443 or newer.

Good at

  • Accurate Persian record classification
  • Image‑based security‑camera queries
  • Receipt total verification

Limits

  • No text generation
  • Not suitable for person identification
  • Requires vision projector for image input

Best for

  • Enterprise decision support
  • Retail receipt analysis
  • Security camera monitoring

Who it’s for. Developers building Persian‑first decision systems that need both text and image understanding. The model is ideal for applications requiring calibrated probability outputs rather than free‑form generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 3.5 GB
Fits Get file →
Q3_K_S2.1 GB 3.6 GB
Fits Get file →
Q3_K_M2.3 GB 3.8 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 4.1 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 4.6 GB
Fits Get file →
Q6_K3.5 GB 5.0 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, ~4.3 GB memory at 8k context). For 4 GB VRAM, Q3_K_M (2.26 GB, ~3.8 GB memory). If you have 16 GB VRAM, Q8_0 (4.48 GB, ~6.1 GB memory) offers higher precision.

What GPU do you need for Mizan v2 4B?

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 5.0 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 Mizan v2 4B quant should you choose?

Q4_K_M is the usual starting point for Mizan v2 4B: 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
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMizan
Licenseapache-2.0
Downloads (HF)1,042
Last updated2026-10-14

Frequently asked questions about Mizan v2 4B

How much VRAM does Mizan v2 4B 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 Mizan v2 4B 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 Mizan v2 4B 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 Mizan v2 4B 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 4.3 GB at 32K.

Where can I download Mizan v2 4B GGUF?

The files are on Hugging Face in the mradermacher/Mizan-v2-4B-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 Mizan v2 4B 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 Mizan v2 4B on 8 GB VRAM?

Yes, use the Q4_K_M quant which is 2.71 GB and requires about 4.3 GB of VRAM at 8k context.

Does the model support image input?

Yes, add the 0.37 GB vision projector to the main GGUF for image processing.

Is the model suitable for person identification?

No, it was trained only on presence and behaviour questions and should not be used for identifying people.

Other GGUFs of Mizan-v2-4B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mizan models

All Mizan →

Other small models

All small models →