PA

Paath E4B Merged

PaathGGUF by mradermacherUpdated 2026-10-10
Download on Hugging Face
Parameters7.52B
Context128K
Layers42
Architecturegemma4
Smallest quant4.4 GB
Quick answer

Paath E4B Merged needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 4.4 GB (Q2_K) to 15.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Paath E4B Merged – offline multilingual Gemma4 model for Indian education

Paath E4B Merged is a Gemma4-based model fine‑tuned with QLoRA for offline tutoring. It supports reasoning, tools, and vision. The model is licensed under apache‑2.0 and trained on 131072 context tokens.

Good at

  • Multilingual teaching
  • Reasoning tasks
  • Vision integration

Limits

  • No internet required but no cloud support
  • Large VRAM needed for higher quants
  • No explicit vision benchmarks

Best for

  • On‑device tutoring apps
  • Offline educational tools
  • Embedded learning systems

Who it’s for. Developers building offline educational applications for Indian students. The model runs on mid‑range Android phones with no internet, providing a zero‑cost inference experience.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.4 GB 6.3 GB
Fits Get file →
Q3_K_S4.7 GB 6.6 GB
Fits Get file →
Q3_K_M4.9 GB 6.8 GB
Fits Get file →
Q3_K_L5.0 GB 6.9 GB
Fits Get file →
IQ4_XS5.1 GB 7.0 GB
Fits Get file →
Q4_K_S5.2 GB 7.1 GB
Fits Get file →
Q4_K_M5.3 GB 7.2 GB
Tight Get file →
Q5_K_S5.7 GB 7.6 GB
Tight Get file →
Q5_K_M5.8 GB 7.7 GB
Tight Get file →
Q6_K6.2 GB 8.1 GB
Too big Get file →
Q8_08.0 GB 9.9 GB
Too big Get file →
F1615.1 GB 17.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.34 GB, 7.2 GB memory) or Q5_K_M (5.76 GB, 7.7 GB). For 12 GB VRAM, Q6_K (6.22 GB, 8.1 GB) or Q8_0 (8.03 GB, 9.9 GB) are suitable. Lower quants like Q2_K (4.4 GB, 6.3 GB) fit 6 GB VRAM setups.

What GPU do you need for Paath E4B Merged?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.1 GB file, about 17.0 GB in use).

Which Paath E4B Merged quant should you choose?

Q4_K_M is the usual starting point for Paath E4B Merged: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 8.0 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 4.4 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

Architecturegemma4
Parameters7.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymradermacher
FamilyPaath
Licenseapache-2.0
Downloads (HF)98
Last updated2026-10-10

Frequently asked questions about Paath E4B Merged

How much VRAM does Paath E4B Merged need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Paath E4B Merged on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Paath E4B Merged GGUF?

It depends on the quant: Q2_K is 4.4 GB, Q3_K_S is 4.7 GB, Q3_K_M is 4.9 GB, Q3_K_L is 5.0 GB, IQ4_XS is 5.1 GB, Q4_K_S is 5.2 GB and 6 more.

What context length does Paath E4B Merged support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Paath E4B Merged GGUF?

The files are on Hugging Face in the mradermacher/paath-e4b-merged-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 Paath E4B Merged 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 Paath E4B Merged on a GPU with 8 GB VRAM?

Yes, the Q4_K_M quant uses about 7.2 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

Yes, vision is listed as an ability, but no specific vision benchmarks are provided.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other small models

All small models →