UN

unbound e2b

UnboundGGUF by evalengineUpdated 2026-05-20
Download on Hugging Face
Parameters4.63B
Context128K
Layers35
Architecturegemma4
Smallest quant3.0 GB
Quick answer

unbound e2b needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 3.0 GB (Q2_K) to 4.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Unbound E2B – uncensored Gemma‑4 finetune with optional vision

Unbound E2B is a 4.63B‑parameter Gemma‑4 model fine‑tuned by Eval Engine. It runs on-device via GGUF and supports optional image‑to‑text through a separate vision projector. The model offers reduced safety filtering and no API or refusal limits.

Good at

  • Reasoning
  • Tool usage
  • Vision (optional)

Limits

  • No safety filtering – can produce harmful content
  • No API – runs locally only
  • Requires 131072 context tokens for full capability

Best for

  • Local LLM deployment
  • Creative writing with low temperature control
  • Image‑to‑text tasks with mmproj

Who it’s for. Developers and researchers needing a fully on‑device, uncensored Gemma‑4 model. Suitable for applications that can handle potential unsafe outputs and require local inference without external APIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB (3 parts) 4.1 GB
Fits Get file →
Q3_K_M3.2 GB (3 parts) 4.3 GB
Fits Get file →
Q4_K_M3.4 GB (3 parts) 4.5 GB
Fits Get file →
Q6_K3.8 GB (4 parts) 4.9 GB
Fits Get file →
Q8_04.9 GB (4 parts) 6.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 3.42 GB, ~4.5 GB memory at 8 k context). For 12 GB VRAM, Q6_K (3.83 GB, ~4.9 GB memory). For 16 GB VRAM, Q8_0 (4.95 GB, ~6 GB memory). Shard counts are 3 or 4 parts as listed.

What GPU do you need for unbound 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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).

Which unbound e2b quant should you choose?

Q4_K_M is the usual starting point for unbound e2b: it balances file size and quality well. Here it is a 3.4 GB file.

The Q8_0 file is 4.9 GB, about 1.4 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 3.0 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
Parameters4.63B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Source

Quantized byevalengine
FamilyUnbound
Licenseapache-2.0
Downloads (HF)828
Last updated2026-05-20

Frequently asked questions about unbound e2b

How much VRAM does unbound e2b need?

About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 unbound 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 unbound e2b GGUF?

It depends on the quant: Q2_K is 3.0 GB, Q3_K_M is 3.2 GB, Q4_K_M is 3.4 GB, Q6_K is 3.8 GB, Q8_0 is 4.9 GB.

What context length does unbound 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 unbound e2b GGUF?

The files are on Hugging Face in the evalengine/unbound-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 unbound 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 Unbound E2B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 4.5 GB memory at 8 k context, which fits 8 GB VRAM with headroom.

Does Unbound E2B support image input?

Yes, pair any LM quant with the mmproj-unbound-e2b.gguf projector for image‑to‑text. The projector is ~942 MB.

Is there an API for Unbound E2B?

No, the model runs locally via Ollama, llama.cpp, LM Studio, or wllama; no external API is provided.

Other GGUFs of unbound-e2b

Similar models

Browse all →

More from evalengine

All by evalengine →

More Unbound models

All Unbound →

Other small models

All small models →