GE

Gemma 4 1B 0.8B Tiny

GemmaGGUF by mradermacherUpdated 2026-10-16
Download on Hugging Face
Parameters977M
Context256K
Layers6
Architecturegemma4
Smallest quant0.6 GB
Quick answer

Gemma 4 1B 0.8B Tiny needs about 2.0 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.6 GB (Q2_K) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Gemma 4 1B 0.8B Tiny – a small, MoE-enabled Gemma4 model

Gemma 4 1B 0.8B Tiny is a 0.977B parameter model with a mixture of experts. It supports a 262144 token context and is available in multiple GGUF quantizations. The model is intended for testing and development rather than production use.

Good at

  • Low‑memory inference
  • MoE experimentation
  • Fast prototyping

Limits

  • No vision fine‑tuning
  • Not production‑ready
  • License not specified

Best for

  • Testing quantization techniques
  • Debugging transformer pipelines
  • Developing lightweight LLM apps

Who it’s for. Developers and researchers who need a small Gemma4 variant for rapid experimentation. The model is suitable for environments with limited GPU memory and for validating new quantization methods.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.6 GB 1.9 GB
Fits Get file →
Q3_K_S0.6 GB 2.0 GB
Fits Get file →
Q3_K_M0.7 GB 2.0 GB
Fits Get file →
Q3_K_L0.7 GB 2.0 GB
Fits Get file →
IQ4_XS0.7 GB 2.0 GB
Fits Get file →
Q4_K_S0.7 GB 2.0 GB
Fits Get file →
Q4_K_M0.7 GB 2.0 GB
Fits Get file →
Q5_K_S0.8 GB 2.1 GB
Fits Get file →
Q5_K_M0.8 GB 2.1 GB
Fits Get file →
Q6_K0.8 GB 2.1 GB
Fits Get file →
Q8_01.1 GB 2.4 GB
Fits Get file →
F162.0 GB 3.3 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.72 GB, 2 GB memory) or Q5_K_S (0.76 GB, 2.1 GB memory). If 4 GB VRAM is available, Q2_K (0.62 GB, 1.9 GB memory) is recommended. Larger VRAM allows higher‑quality quants such as F16 (1.97 GB, 3.3 GB memory).

What GPU do you need for Gemma 4 1B 0.8B Tiny?

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 3.3 GB in use).

Which Gemma 4 1B 0.8B Tiny quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 1B 0.8B Tiny: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.1 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 0.6 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
Parameters977M (approximate, mixture of experts)
Layers6
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyGemma
Downloads (HF)1,469
Last updated2026-10-16

Frequently asked questions about Gemma 4 1B 0.8B Tiny

How much VRAM does Gemma 4 1B 0.8B Tiny need?

About 2.0 GB at Q4_K_M with an 8K context window. That is the 0.7 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 4 1B 0.8B Tiny on an 8 GB GPU?

Yes, with F16: the 2.0 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 4 1B 0.8B Tiny GGUF?

It depends on the quant: Q2_K is 0.6 GB, Q3_K_S is 0.6 GB, Q3_K_M is 0.7 GB, Q3_K_L is 0.7 GB, IQ4_XS is 0.7 GB, Q4_K_S is 0.7 GB and 6 more.

What context length does Gemma 4 1B 0.8B Tiny support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Gemma 4 1B 0.8B Tiny GGUF?

The files are on Hugging Face in the mradermacher/gemma-4-1B-0.8B-tiny-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_S will fit within 8 GB VRAM with an estimated 2–2.1 GB memory usage.

Does this model support vision tasks?

The architecture includes vision components, but they are not fine‑tuned and not validated for vision use.

What is the context length of this model?

The model supports a 262144 token context length.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other tiny models

All tiny models →