Gemma4 Hermes Tools needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma4 Hermes Tools – 25.2B parameter LLM fine‑tuned for tool use
Gemma4 Hermes Tools is a 25.2B parameter model based on google/gemma-4-26B-A4B-it. It is fine‑tuned for reliable function calling and tool use. The model supports a 262144 token context window and is available in a Q4_K_M quantized GGUF format.
Good at
- Tool use and function calling
- Reasoning tasks
- Multimodal input handling
Limits
- Requires 25.3 GB VRAM at 8k context
- No vision support in the quantized file
- License: gemma (Apache 2.0)
Best for
- Agentic pipelines needing structured tool calls
- Local inference on laptops with 8+ GB VRAM
- Fine‑tuned instruction following
Who it’s for. Developers building agentic applications that require reliable tool invocation. The model is suitable for local deployment on devices with sufficient VRAM and for users who need a Gemini‑style model with function‑calling capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 16.8 GB | 25.3 GB | Too big | Get file → |
The only available quant is Q4_K_M, file size 16.8 GB. It requires approximately 25.3 GB VRAM at 8k context. For lower VRAM budgets, a higher‑bit quant would be needed, but none is provided here.
What GPU do you need for Gemma4 Hermes Tools?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_M (16.8 GB file, about 25.3 GB in use).
Which Gemma4 Hermes Tools quant should you choose?
Q4_K_M is the usual starting point for Gemma4 Hermes Tools: it balances file size and quality well. Here it is a 16.8 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma4 Hermes Tools
How much VRAM does Gemma4 Hermes Tools need?
About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Gemma4 Hermes Tools on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 25.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma4 Hermes Tools GGUF?
It depends on the quant: Q4_K_M is 16.8 GB.
What context length does Gemma4 Hermes Tools support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Gemma4 Hermes Tools GGUF?
The files are on Hugging Face in the brokencircuitranch/gemma4-hermes-tools repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Gemma4 Hermes Tools 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 Gemma4 Hermes Tools on 8 GB VRAM?
No. The Q4_K_M quant requires about 25.3 GB VRAM at 8k context, exceeding 8 GB.
Does the model support image input?
The base Gemma4 model supports multimodal input, but the quantized file does not specify vision support.
What license applies to this model?
The model inherits the gemma license, which is Apache 2.0.