VI

Vigyan 1.5B 4x MoE

VigyanGGUF by mradermacherUpdated 2026-10-06
Download on Hugging Face
Parameters6.4B
Context128K
Layers28
Architectureqwen2moe
Smallest quant2.4 GB
Quick answer

Vigyan 1.5B 4x MoE needs about 4.7 GB of memory at Q4_K_M (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.4 GB (Q2_K) to 12.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Vigyan 1.5B 4x MoE – a sparse mixture of experts model

Vigyan 1.5B 4x MoE is a 6.4B parameter model built on Qwen2MoE architecture. It stitches four domain experts (Science, Technology, Engineering, Mathematics) onto a 1.5B base. The model supports 131072 context tokens and is released under cc‑by‑nc‑4.0.

Good at

  • Domain‑specific reasoning
  • Tool usage
  • Low‑latency inference

Limits

  • No vision support
  • Requires at least 3.2 GB VRAM for Q2_K
  • License restricts commercial use

Best for

  • Academic research demos
  • Edge inference on mobile CPUs
  • Rapid prototyping of domain experts

Who it’s for. Researchers and developers who need a compact MoE model for single‑expert inference. The model is suitable for experimentation and educational purposes, not for commercial deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.4 GB 3.2 GB
Fits Get file →
Q3_K_S2.8 GB 3.6 GB
Fits Get file →
Q3_K_M3.1 GB 3.9 GB
Fits Get file →
Q3_K_L3.4 GB 4.1 GB
Fits Get file →
IQ4_XS3.5 GB 4.2 GB
Fits Get file →
Q4_K_S3.7 GB 4.4 GB
Fits Get file →
Q4_K_M3.9 GB 4.7 GB
Fits Get file →
Q5_K_S4.4 GB 5.2 GB
Fits Get file →
Q5_K_M4.6 GB 5.3 GB
Fits Get file →
Q6_K5.3 GB 6.0 GB
Fits Get file →
Q8_06.8 GB 7.5 GB
Tight Get file →
F1612.8 GB 13.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 3.92 GB, estimated 4.7 GB memory). If 12 GB VRAM is available, Q5_K_M (4.57 GB, 5.3 GB memory) offers higher precision. For the tightest memory budget, Q2_K (2.43 GB, 3.2 GB memory) is the smallest option.

What GPU do you need for Vigyan 1.5B 4x MoE?

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_M (3.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (5.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.8 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (6.8 GB file, about 7.5 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (12.8 GB file, about 13.5 GB in use).

Which Vigyan 1.5B 4x MoE quant should you choose?

Q4_K_M is the usual starting point for Vigyan 1.5B 4x MoE: it balances file size and quality well. Here it is a 3.9 GB file.

The Q8_0 file is 6.8 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 2.4 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

Architectureqwen2moe
Parameters6.4B (approximate, mixture of experts)
Layers28
Trained context131,072 tokens
KV cache (fp16)28 KB per token

Source

Quantized bymradermacher
FamilyVigyan
Downloads (HF)611
Last updated2026-10-06

Frequently asked questions about Vigyan 1.5B 4x MoE

How much VRAM does Vigyan 1.5B 4x MoE need?

About 4.7 GB at Q4_K_M with an 8K context window. That is the 3.9 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 Vigyan 1.5B 4x MoE on an 8 GB GPU?

Yes, with Q8_0: the 6.8 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Vigyan 1.5B 4x MoE GGUF?

It depends on the quant: Q2_K is 2.4 GB, Q3_K_S is 2.8 GB, Q3_K_M is 3.1 GB, Q3_K_L is 3.4 GB, IQ4_XS is 3.5 GB, Q4_K_S is 3.7 GB and 6 more.

What context length does Vigyan 1.5B 4x MoE support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download Vigyan 1.5B 4x MoE GGUF?

The files are on Hugging Face in the mradermacher/Vigyan-1.5B-4x-MoE-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 Vigyan 1.5B 4x MoE use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Vigyan 1.5B 4x MoE on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 4.7 GB VRAM at 8k context, which fits within 8 GB.

Does the model support image input?

No, the model has no vision capabilities.

Is the model free for commercial use?

No, it is licensed under cc‑by‑nc‑4.0, which prohibits commercial use.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Vigyan models

All Vigyan →

Other small models

All small models →