GE

Gemma 2 2b

GemmaGGUF by legraphistaUpdated 2024-07-31
Download on Hugging Face
Parameters2.61B
Context8K
Layers26
Architecturegemma2
Smallest quant0.8 GB
Quick answer

Gemma 2 2b needs about 2.8 GB of memory at IQ3_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 26 quants, from 0.8 GB (IQ1_S) to 10.5 GB (F32).

Gemma 2 2b – 2.61B parameter LLM in GGUF format

Gemma 2 2b is a 2.61B parameter language model from the Gemma family. It is quantized by legraphista and available in multiple GGUF quantizations. The model supports a 8192 token context window.

Good at

  • Text generation
  • Code completion
  • Language understanding

Limits

  • No vision support
  • License: gemma
  • Context limited to 8192 tokens

Best for

  • Chatbots
  • Code assistants
  • Content drafting

Who it’s for. Developers and researchers who need a lightweight Gemma model for local inference. The model is suitable for environments with limited GPU memory and for use with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.8 GB 2.2 GB
Fits Get file →
IQ1_M0.9 GB 2.2 GB
Fits Get file →
IQ2_XXS0.9 GB 2.3 GB
Fits Get file →
IQ2_XS1.0 GB 2.4 GB
Fits Get file →
IQ2_S1.0 GB 2.4 GB
Fits Get file →
IQ2_M1.1 GB 2.5 GB
Fits Get file →
Q2_K_S1.2 GB 2.5 GB
Fits Get file →
IQ3_XXS1.2 GB 2.6 GB
Fits Get file →
Q2_K1.2 GB 2.6 GB
Fits Get file →
IQ3_XS1.3 GB 2.7 GB
Fits Get file →
IQ3_S1.4 GB 2.7 GB
Fits Get file →
Q3_K_S1.4 GB 2.7 GB
Fits Get file →
IQ3_M1.4 GB 2.8 GB
Fits Get file →
Q3_K1.5 GB 2.8 GB
Fits Get file →
Q3_K_L1.6 GB 2.9 GB
Fits Get file →
IQ4_XS1.6 GB 2.9 GB
Fits Get file →
IQ4_NL1.6 GB 3.0 GB
Fits Get file →
Q4_K_S1.6 GB 3.0 GB
Fits Get file →
Q4_K1.7 GB 3.1 GB
Fits Get file →
Q5_K_S1.9 GB 3.3 GB
Fits Get file →
Q5_K1.9 GB 3.3 GB
Fits Get file →
Q6_K2.2 GB 3.5 GB
Fits Get file →
Q8_02.8 GB 4.2 GB
Fits Get file →
BF165.2 GB 6.6 GB
Fits Get file →
—5.2 GB 6.6 GB
Fits Get file →
F3210.5 GB 11.8 GB
Too big Get file →

For 8 GB VRAM, use IQ2_S (1 GB) or Q2_K_S (1.64 GB). For 12 GB VRAM, Q3_K (1.46 GB) or Q4_K (1.71 GB) are good choices. For 16 GB VRAM, Q5_K (1.92 GB) or Q6_K (2.15 GB) provide higher quality.

What GPU do you need for Gemma 2 2b?

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 Q6_K (2.2 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.8 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.2 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is F32 (10.5 GB file, about 11.8 GB in use).

Which Gemma 2 2b quant should you choose?

IQ3_M (1.4 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 0.8 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

Architecturegemma2
Parameters2.61B
Layers26
Trained context8,192 tokens
KV cache (fp16)104 KB per token

Source

Quantized bylegraphista
FamilyGemma
Licensegemma
Downloads (HF)1,909
Last updated2024-07-31

Frequently asked questions about Gemma 2 2b

How much VRAM does Gemma 2 2b need?

About 2.8 GB at IQ3_M with an 8K context window. That is the 1.4 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 Gemma 2 2b on an 8 GB GPU?

Yes, with BF16: the 5.2 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 2 2b GGUF?

It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.0 GB, IQ2_M is 1.1 GB and 20 more.

What context length does Gemma 2 2b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.

Where can I download Gemma 2 2b GGUF?

The files are on Hugging Face in the legraphista/gemma-2-2b-IMat-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 Gemma 2 2b 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 2 2b on 8 GB VRAM?

Yes, use a quantization such as IQ2_S or Q2_K_S, which require about 2.5 GB of VRAM at 8k context.

What is the context length of this model?

The model supports up to 8192 tokens of context.

Does this model support image input?

No, the Gemma 2 2b model does not have vision capabilities.

Other GGUFs of gemma-2-2b

Similar models

Browse all →

More from legraphista

All by legraphista →

More Gemma models

All Gemma →

Other tiny models

All tiny models →