Mizan v3 3B needs about 3.2 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 18 quants, from 1.5 GB (Q2_K) to 5.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Mizan v3 3B – Persian-first decision model in GGUF
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 is optimized for Persian and English records. The model is available in multiple GGUF quantizations.
Good at
- Fast single-pass decision making
- Calibrated probability outputs
- Supports Persian and English records
Limits
- No vision support
- No text generation
- No imatrix quantization
Best for
- Routing policy enforcement
- Decision scoring for Persian datasets
- Fast inference on entry‑level GPUs
Who it’s for. Developers and data scientists who need a lightweight decision model for Persian or English records. The model is suitable for applications that require rule‑based routing or scoring without generating text.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 2.9 GB | Fits | Get file → | |
| IQ3_M | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_M | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_L | 1.8 GB | 3.0 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 3.0 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 3.1 GB | Fits | Get file → | |
| IQ4_NL | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q4_1 | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_M | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_L | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 3.5 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q6_K_L | 2.7 GB | 3.9 GB | Fits | Get file → | |
| Q8_0 | 3.1 GB | 4.3 GB | Fits | Get file → | |
| BF16 | 5.8 GB | 7.0 GB | Fits | Get file → |
For the smallest memory footprint, use Q2_K (1.51 GB file, 2.7 GB VRAM at 8k context). For balanced quality and memory, Q4_K_M (2.03 GB file, 3.2 GB VRAM). If memory allows, Q8_0 (3.1 GB file, 4.3 GB VRAM) gives the highest fidelity.
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_L (2.7 GB file, about 3.9 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 BF16 (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 2.0 GB file.
The Q8_0 file is 3.1 GB, about 1.5 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 1.5 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 3.2 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 Mizan v3 3B on an 8 GB GPU?
Yes, with BF16: 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 1.5 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.7 GB, Q3_K_M is 1.8 GB, Q3_K_L is 1.8 GB, IQ4_XS is 1.8 GB and 12 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 bartowski/Nimruz_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 a GPU with 8 GB VRAM?
Yes, the Q4_0 quantization uses about 3.1 GB VRAM at 8k context, which fits within 8 GB. Lower quants use even less memory.
Does Mizan v3 3B support vision?
No, the v3 model has no vision capability. Use v2 if image input is required.