RI

Ringg Router E2B

RinggGGUF by bartowskiUpdated 2026-09-29
Download on Hugging Face
Parameters4.63B
Context128K
Layers35
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Ringg Router E2B needs about 4.3 GB of memory at Q4_K_M (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 23 quants, from 0.0 GB to 9.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Ringg Router E2B – a 4.63B Gemma‑4 decision model for multilingual voice agents

Ringg Router E2B is a 4.63B parameter Gemma‑4 model fine‑tuned for routing and intent decisions in voice and chat agents. It handles short conversations and a list of options, returning a JSON object with the chosen option, extracted values, and a one‑sentence rationale. The model supports Indian languages and code‑mixed text.

Good at

  • Fast routing decisions in voice agents
  • Structured extraction from short conversations
  • Multilingual Indian language support

Limits

  • No vision or audio support without mmproj
  • Requires 8k context for memory estimates
  • License is Apache‑2.0

Best for

  • IVR replacements
  • Tool selection in chatbots
  • Short conversation triage

Who it’s for. Developers building voice or chat agents that need quick routing and intent decisions. The model is suitable for multilingual Indian use cases and supports structured extraction of named fields.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.1 GB
Fits Get file →
IQ2_M2.0 GB 3.0 GB
Fits Get file →
Q2_K2.3 GB 3.4 GB
Fits Get file →
IQ3_XXS2.4 GB 3.5 GB
Fits Get file →
Q3_K_S2.5 GB 3.6 GB
Fits Get file →
IQ3_XS2.5 GB 3.6 GB
Fits Get file →
Q3_K_M2.5 GB 3.6 GB
Fits Get file →
Q3_K_L2.6 GB 3.7 GB
Fits Get file →
IQ3_M2.6 GB 3.7 GB
Fits Get file →
IQ4_XS3.0 GB 4.1 GB
Fits Get file →
Q4_K_S3.1 GB 4.2 GB
Fits Get file →
IQ4_NL3.2 GB 4.3 GB
Fits Get file →
Q4_K_M3.2 GB 4.3 GB
Fits Get file →
Q4_K_L3.3 GB 4.4 GB
Fits Get file →
Q4_03.4 GB 4.5 GB
Fits Get file →
Q4_13.5 GB 4.6 GB
Fits Get file →
Q5_K_S3.6 GB 4.7 GB
Fits Get file →
Q5_K_M3.7 GB 4.8 GB
Fits Get file →
Q6_K_S3.9 GB 5.0 GB
Fits Get file →
Q6_K3.9 GB 5.0 GB
Fits Get file →
Q6_K_L4.0 GB 5.1 GB
Fits Get file →
Q8_04.9 GB 6.0 GB
Fits Get file →
BF169.3 GB 10.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (3.17 GB) or Q4_K_S (3.08 GB). For 6 GB VRAM, Q4_K_L (3.30 GB) is a good balance. If you have 4 GB VRAM, IQ3_XXS (2.44 GB) or Q3_K_S (2.47 GB) provide acceptable size. Memory estimates are approximate.

What GPU do you need for Ringg Router E2B?

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 IQ3_M (2.6 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (9.3 GB file, about 10.4 GB in use).

Which Ringg Router E2B quant should you choose?

Q4_K_M is the usual starting point for Ringg Router E2B: it balances file size and quality well. Here it is a 3.2 GB file.

The Q8_0 file is 4.9 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters4.63B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Source

Quantized bybartowski
FamilyRingg
Licenseapache-2.0
Downloads (HF)3,537
Last updated2026-09-29

Frequently asked questions about Ringg Router E2B

How much VRAM does Ringg Router E2B need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 3.2 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 Ringg Router E2B on an 8 GB GPU?

Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ringg Router E2B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 2.0 GB, Q2_K is 2.3 GB, IQ3_XXS is 2.4 GB, Q3_K_S is 2.5 GB, IQ3_XS is 2.5 GB and 17 more.

What context length does Ringg Router E2B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download Ringg Router E2B GGUF?

The files are on Hugging Face in the bartowski/RinggAI_ringg-router-e2b-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 Ringg Router E2B 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 Ringg Router E2B on 8 GB VRAM?

Yes, use Q4_K_M (3.17 GB) or Q4_K_S (3.08 GB) quantizations. The model will fit within 8 GB VRAM with 8k context.

Does this model support image or audio input?

The base model does not support vision or audio. Multimodal support requires the mmproj files and a compatible quantization.

What license applies to Ringg Router E2B?

The model is released under the Apache‑2.0 license.

Other GGUFs of ringg-router-e2b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Ringg models

All Ringg →

Other small models

All small models →