GE

Locus Gemma 4 E2B

GemmaGGUF by mradermacherUpdated 2026-05-15
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Locus Gemma 4 E2B 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 25 quants, from 0.0 GB to 6.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Gemma‑4‑E2B: a clean, RLHF‑voice‑removed base model

Locus Gemma 4 E2B is a 7.46B‑parameter Gemma‑4 model stripped of corporate‑voice RLHF patterns. It retains all core capabilities and safety but is unpolished for chat. The model can be fine‑tuned for custom personalities or tasks.

Good at

  • Clean substrate for fine‑tuning
  • No corporate‑voice preambles
  • Reasoning without hedging boilerplate

Limits

  • Not instruction‑tuned for chat
  • No vision support unless mmproj files are added
  • Large context 131072 tokens may need more VRAM

Best for

  • Fine‑tuning custom personas
  • Coding assistants without preambles
  • Reasoning tasks that need concise output

Who it’s for. Developers and researchers who want a base Gemma‑4 model free from RLHF voice patterns and ready for their own alignment or fine‑tuning. It is suitable for those who prefer to build personality or task‑specific models from a clean foundation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.9 GB
Fits Get file →
IQ1_S3.3 GB 5.2 GB
Fits Get file →
IQ1_M3.4 GB 5.3 GB
Fits Get file →
IQ2_XXS3.5 GB 5.4 GB
Fits Get file →
IQ2_XS3.6 GB 5.5 GB
Fits Get file →
IQ2_S3.7 GB 5.6 GB
Fits Get file →
IQ2_M3.8 GB 5.7 GB
Fits Get file →
IQ3_XXS4.0 GB 5.9 GB
Fits Get file →
Q2_K_S4.3 GB 6.2 GB
Fits Get file →
Q2_K4.4 GB 6.3 GB
Fits Get file →
IQ3_XS4.5 GB 6.5 GB
Fits Get file →
Q3_K_S4.6 GB 6.5 GB
Fits Get file →
IQ3_S4.6 GB 6.5 GB
Fits Get file →
IQ3_M4.7 GB 6.6 GB
Fits Get file →
Q3_K_M4.8 GB 6.7 GB
Fits Get file →
Q3_K_L5.0 GB 6.9 GB
Fits Get file →
IQ4_XS5.0 GB 6.9 GB
Fits Get file →
IQ4_NL5.2 GB 7.1 GB
Fits Get file →
Q4_05.2 GB 7.1 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 →
Q4_15.4 GB 7.3 GB
Tight Get file →
Q5_K_S5.6 GB 7.6 GB
Tight Get file →
Q5_K_M5.7 GB 7.6 GB
Tight Get file →
Q6_K6.2 GB 8.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.29 GB, estimated 5.2 GB memory). For 12 GB VRAM, Q4_K_M (file size 5.3 GB, estimated 7.2 GB memory) offers a good balance. For 16 GB VRAM, Q5_K_M (file size 5.72 GB, estimated 7.6 GB memory) gives higher quality.

What GPU do you need for Locus Gemma 4 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 the main file (0.0 GB file, about 1.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_XXS (4.0 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 8.1 GB in use).

Which Locus Gemma 4 E2B quant should you choose?

Q4_K_M is the usual starting point for Locus Gemma 4 E2B: it balances file size and quality well. Here it is a 5.3 GB file.

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
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licensegemma
Downloads (HF)2,241
Last updated2026-05-15

Frequently asked questions about Locus Gemma 4 E2B

How much VRAM does Locus Gemma 4 E2B 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 Locus Gemma 4 E2B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Locus Gemma 4 E2B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.4 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.6 GB, IQ2_S is 3.7 GB and 19 more.

What context length does Locus Gemma 4 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 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Locus Gemma 4 E2B GGUF?

The files are on Hugging Face in the mradermacher/locus-gemma-4-e2b-i1-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 Locus Gemma 4 E2B use?

Hugging Face lists the license as gemma. 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 Locus Gemma 4 E2B on 8 GB VRAM?

Yes, the IQ1_S quant uses about 5.2 GB memory at 8 k context, fitting within 8 GB VRAM.

Does this model support vision tasks?

Vision support requires mmproj files, which are not included in the current GGUF set.

Is this model chat‑ready?

No, it is not instruction‑tuned for chat and will produce less polished responses out of the box.

Other GGUFs of locus-gemma-4-e2b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →