GE

TheDrummer Gemmasutra Small 4B v1

GemmaGGUF by bartowskiUpdated 2025-03-11
Download on Hugging Face
Parameters3.86B
Context8K
Layers42
Architecturegemma2
Smallest quant1.5 GB
Quick answer

TheDrummer Gemmasutra Small 4B v1 needs about 4.4 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.5 GB (IQ2_M) to 7.7 GB (BF16).

Gemma2 4B model with 8192 token context

TheDrummer Gemmasutra Small 4B v1 is a Gemma2 architecture model with 3.86B parameters. It supports a 8192 token context window and is available in multiple GGUF quantizations. The model is provided by bartowski and is based on TheDrummer/Gemmasutra-Small-4B-v1.

Good at

  • Short‑form conversational tasks
  • Lightweight inference on modest GPUs
  • Quick prototyping with low memory footprint

Limits

  • No vision support
  • No system prompt support
  • License not specified

Best for

  • Chatbots on edge devices
  • Rapid experimentation
  • Educational demos

Who it’s for. Developers and researchers who need a small, efficient Gemma2 model for local deployment. The model is suitable for those working with llama.cpp or LM Studio and who prefer a lightweight quantized version.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M1.5 GB 3.4 GB
Fits Get file →
IQ3_XXS1.7 GB 3.6 GB
Fits Get file →
Q2_K1.7 GB 3.6 GB
Fits Get file →
IQ3_XS1.8 GB 3.7 GB
Fits Get file →
Q2_K_L1.8 GB 3.7 GB
Fits Get file →
Q3_K_S1.9 GB 3.8 GB
Fits Get file →
IQ3_M2.0 GB 3.9 GB
Fits Get file →
Q3_K_M2.1 GB 4.0 GB
Fits Get file →
Q3_K_L2.2 GB 4.1 GB
Fits Get file →
IQ4_XS2.2 GB 4.1 GB
Fits Get file →
IQ4_NL2.3 GB 4.2 GB
Fits Get file →
Q4_02.3 GB 4.2 GB
Fits Get file →
Q4_K_S2.3 GB 4.3 GB
Fits Get file →
Q3_K_XL2.3 GB 4.3 GB
Fits Get file →
Q4_K_M2.5 GB 4.4 GB
Fits Get file →
Q4_12.5 GB 4.4 GB
Fits Get file →
Q4_K_L2.6 GB 4.5 GB
Fits Get file →
Q5_K_S2.7 GB 4.6 GB
Fits Get file →
Q5_K_M2.8 GB 4.7 GB
Fits Get file →
Q5_K_L2.9 GB 4.9 GB
Fits Get file →
Q6_K3.2 GB 5.1 GB
Fits Get file →
Q6_K_L3.3 GB 5.2 GB
Fits Get file →
Q8_04.1 GB 6.0 GB
Fits Get file →
BF167.7 GB 9.6 GB
Too big Get file →

For 8 GB VRAM, use IQ4_0 (file size 2.34 GB, memory 4.2 GB). For 4 GB VRAM, IQ2_K (1.69 GB, 3.6 GB) is a good choice. If you have 16 GB VRAM, Q4_K_L (2.6 GB, 4.5 GB) offers higher quality.

What GPU do you need for TheDrummer Gemmasutra Small 4B v1?

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 Q3_K_M (2.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.7 GB file, about 9.6 GB in use).

Which TheDrummer Gemmasutra Small 4B v1 quant should you choose?

Q4_K_M is the usual starting point for TheDrummer Gemmasutra Small 4B v1: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.1 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 IQ2_M at 1.5 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

Architecturegemma2
Parameters3.86B
Layers42
Trained context8,192 tokens
KV cache (fp16)168 KB per token

Source

Quantized bybartowski
FamilyGemma
Downloads (HF)1,875
Last updated2025-03-11

Frequently asked questions about TheDrummer Gemmasutra Small 4B v1

How much VRAM does TheDrummer Gemmasutra Small 4B v1 need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.5 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 TheDrummer Gemmasutra Small 4B v1 on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TheDrummer Gemmasutra Small 4B v1 GGUF?

It depends on the quant: IQ2_M is 1.5 GB, IQ3_XXS is 1.7 GB, Q2_K is 1.7 GB, IQ3_XS is 1.8 GB, Q2_K_L is 1.8 GB, Q3_K_S is 1.9 GB and 18 more.

What context length does TheDrummer Gemmasutra Small 4B v1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.4 GB at 8K and 1.4 GB at 8K.

Where can I download TheDrummer Gemmasutra Small 4B v1 GGUF?

The files are on Hugging Face in the bartowski/TheDrummer_Gemmasutra-Small-4B-v1-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, the IQ4_0 quantization requires about 4.2 GB of VRAM at 8k context.

Does this model support a system prompt?

No, the model does not support a system prompt.

What is the context length of this model?

The model supports a context length of 8192 tokens.

Other GGUFs of Gemmasutra-Small-4B-v1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Gemma models

All Gemma →

Other small models

All small models →