GE

Gemma 3 1b It Heretic

GemmaGGUF by saidutta69Updated 2026-10-28
Download on Hugging Face
Parameters1B
Context32K
Layers26
Architecturegemma3
Smallest quant0.8 GB
Quick answer

Gemma 3 1b It Heretic needs about 1.5 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.8 GB (Q4_K_M) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Gemma 3 1b It Heretic – a decensored, refusal‑free Gemma 3 instruct model

Gemma 3 1b It Heretic is a 1.0B‑parameter model derived from google/gemma-3-1b-it. It removes refusal guardrails via targeted weight edits while preserving the base model’s knowledge and instruction‑following. The model is lightweight and suitable for edge devices.

Good at

  • Running on low‑resource hardware
  • Maintaining instruction compliance
  • Providing decensored responses

Limits

  • No vision support
  • Requires 8k context for full memory estimate
  • License is gemma

Best for

  • Edge device inference
  • CPU‑only deployments
  • Small‑scale instruction tasks

Who it’s for. Developers needing a small Gemma 3 instruct model without refusal behavior, suitable for Raspberry Pi class hardware and tiny edge devices. The model offers the same capabilities as the base gemma‑3‑1b‑it but with removed guardrails.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.8 GB 1.5 GB
Fits Get file →
Q5_K_M0.9 GB 1.6 GB
Fits Get file →
Q6_K1.0 GB 1.7 GB
Fits Get file →
Q8_01.1 GB 1.8 GB
Fits Get file →
F162.0 GB 2.7 GB
Fits Get file →

For 8 GB VRAM, the Q4_K_M quant (~0.81 GB) uses an estimated 1.5 GB at 8k context and is recommended. If more memory is available, Q5_K_M (~0.85 GB) or Q6_K (~1.01 GB) can be used. For the highest quality, F16 (~2.01 GB) is available but requires more VRAM.

What GPU do you need for Gemma 3 1b It Heretic?

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 F16 (2.0 GB file, about 2.7 GB in use).

Which Gemma 3 1b It Heretic quant should you choose?

Q4_K_M is the usual starting point for Gemma 3 1b It Heretic: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.1 GB, about 1.3 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters1B
Layers26
Trained context32,768 tokens
KV cache (fp16)26 KB per token

Source

Quantized bysaidutta69
FamilyGemma
Licensegemma
Downloads (HF)658
Last updated2026-10-28

Frequently asked questions about Gemma 3 1b It Heretic

How much VRAM does Gemma 3 1b It Heretic need?

About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.8 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 Gemma 3 1b It Heretic on an 8 GB GPU?

Yes, with F16: the 2.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 3 1b It Heretic GGUF?

It depends on the quant: Q4_K_M is 0.8 GB, Q5_K_M is 0.9 GB, Q6_K is 1.0 GB, Q8_0 is 1.1 GB, F16 is 2.0 GB.

What context length does Gemma 3 1b It Heretic support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Gemma 3 1b It Heretic GGUF?

The files are on Hugging Face in the saidutta69/gemma-3-1b-it-heretic repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Gemma 3 1b It Heretic 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 Gemma 3 1b It Heretic on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 1.5 GB at 8k context, well within 8 GB VRAM limits.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the context length supported?

The model was trained on 32,768 tokens and supports up to that context length.

Other GGUFs of gemma-3-1b-it

Similar models

Browse all →

More from saidutta69

All by saidutta69 →

More Gemma models

All Gemma →

Other tiny models

All tiny models →