GE

Gemma 7b

GemmaGGUF by fedric95Updated 2024-08-22
Download on Hugging Face
Parameters8.54B
Context8K
Layers28
Architecturegemma
Smallest quant3.5 GB
Quick answer

Gemma 7b needs about 9.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 3.5 GB (Q2_K) to 17.1 GB (BF16).

Gemma 7b – 8.54B parameter LLM in GGUF format

Gemma 7b is a 8.54B parameter language model from Google, released in GGUF format. It supports a 8192 token context window and is available in multiple quantizations for different memory budgets.

Good at

  • Fast inference on modest GPUs
  • Low memory footprint with Q2_K
  • Good token prediction

Limits

  • No vision support
  • License restricts commercial use
  • Requires 8k context for full performance

Best for

  • Chatbot prototypes
  • Text generation on edge devices
  • Rapid prototyping with low VRAM

Who it’s for. Developers and researchers needing a lightweight Gemma model for local inference. Suitable for projects where GPU memory is limited but a reasonably sized language model is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.5 GB 7.7 GB
Tight Get file →
Q3_K_S4.0 GB 8.2 GB
Too big Get file →
Q3_K_M4.4 GB 8.6 GB
Too big Get file →
Q3_K_L4.7 GB 9.0 GB
Too big Get file →
Q4_K_S5.0 GB 9.3 GB
Too big Get file →
Q4_K_M5.3 GB 9.6 GB
Too big Get file →
Q5_K_S6.0 GB 10.2 GB
Too big Get file →
Q5_K_M6.1 GB 10.4 GB
Too big Get file →
Q6_K7.0 GB 11.3 GB
Too big Get file →
Q8_09.1 GB 13.3 GB
Too big Get file →
BF1617.1 GB 21.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 3.48 GB, estimated 7.7 GB memory). For 12 GB VRAM, Q4_K_M (5.33 GB, 9.6 GB memory). For 16 GB VRAM, Q5_K_M (6.14 GB, 10.4 GB memory).

What GPU do you need for Gemma 7b?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q2_K (3.5 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 13.3 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.1 GB file, about 21.3 GB in use).

Which Gemma 7b quant should you choose?

Q4_K_M is the usual starting point for Gemma 7b: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 9.1 GB, about 1.7 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 3.5 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

Architecturegemma
Parameters8.54B
Layers28
Trained context8,192 tokens
KV cache (fp16)448 KB per token

Source

Quantized byfedric95
FamilyGemma
Base modelgoogle/gemma-7b
Licensegemma
Downloads (HF)607
Last updated2024-08-22

Frequently asked questions about Gemma 7b

How much VRAM does Gemma 7b need?

About 9.6 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 Gemma 7b on an 8 GB GPU?

Yes, with Q2_K: the 3.5 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 7b GGUF?

It depends on the quant: Q2_K is 3.5 GB, Q3_K_S is 4.0 GB, Q3_K_M is 4.4 GB, Q3_K_L is 4.7 GB, Q4_K_S is 5.0 GB, Q4_K_M is 5.3 GB and 5 more.

What context length does Gemma 7b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.8 GB at 8K and 3.8 GB at 8K.

Where can I download Gemma 7b GGUF?

The files are on Hugging Face in the fedric95/gemma-7b-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 7b 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 7b on 8 GB VRAM?

Yes, the Q2_K quantization requires approximately 7.7 GB memory at 8k context, fitting within 8 GB VRAM.

Does Gemma 7b support image input?

No, the model does not include vision capabilities.

What is the maximum context length for Gemma 7b?

The model supports a maximum context length of 8192 tokens.

Other GGUFs of gemma-7b

Similar models

Browse all →

More from fedric95

All by fedric95 →

More Gemma models

All Gemma →

Other small models

All small models →