Mizan v3 3B needs about 3.1 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.4 GB (Q2_K) to 5.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Mizan v3 3B – Persian‑first decision model
Mizan v3 3B is a 2.9B parameter decision model that returns calibrated probabilities for typed questions. It operates in a single forward pass and supports Persian and English queries. The model is released under Apache‑2.0 and is trained only on data that allows commercial use.
Good at
- Calibrated probability outputs
- Fast inference – 55 ms on entry‑level GPU
- No text generation, no parsing
Limits
- No vision support – use v2 for image data
- Requires 8 k context for memory estimates
- No mixture of experts
Best for
- Routing policies and scoring rubrics
- Decision tasks on Persian records
- Fast inference on low‑end GPUs
Who it’s for. Developers needing a lightweight Persian‑first decision engine that can be integrated via the /v1/systemone API. Suitable for applications that require calibrated probability outputs without text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.9 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_S | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 3.1 GB | 4.3 GB | Fits | Get file → | |
| F16 | 5.8 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K_M quant (1.93 GB file, 3.1 GB memory at 8 k context) is a good balance of size and performance. If memory is tighter, Q3_K_M (1.62 GB, 2.8 GB memory) is suitable. For the smallest footprint, Q2_K (1.41 GB, 2.6 GB memory) works on 4 GB VRAM systems.
What GPU do you need for Mizan v3 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 Q6_K (2.4 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.1 GB file, about 4.3 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.8 GB file, about 7.0 GB in use).
Which Mizan v3 3B quant should you choose?
Q4_K_M is the usual starting point for Mizan v3 3B: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.1 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.
If memory is tight, the smallest file is Q2_K at 1.4 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
Source
Frequently asked questions about Mizan v3 3B
How much VRAM does Mizan v3 3B need?
About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.9 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 v3 3B on an 8 GB GPU?
Yes, with F16: the 5.8 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mizan v3 3B GGUF?
It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.8 GB and 6 more.
What context length does Mizan v3 3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Mizan v3 3B GGUF?
The files are on Hugging Face in the mradermacher/Mizan-v3-3B-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 Mizan v3 3B 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 v3 3B on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 3.1 GB memory at 8 k context, well within an 8 GB VRAM budget.
Does Mizan v3 support vision?
No, v3 has no vision capability. Use v2 for image data.
What license does Mizan v3 use?
Apache‑2.0, trained only on data that allows commercial use.