gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.3 GB (Q4_K_M) to 15.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI – 7.5B parameter LLM with tool calling
Gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI is a 7.5B parameter model based on the gemma4 architecture. It supports reasoning and tool usage and is available in GGUF format. The model was quantized by deadbydawn101 and is built on the deadbydawn101/gemma-4-E4B-mlx-4bit parent.
Good at
- Reasoning
- Tool calling
- Long context (131072 tokens)
Limits
- No vision support
- Requires 8k context for memory estimates
- License is gemma
Best for
- Local reasoning tasks
- Tool‑enabled agent workflows
- LLM inference on Apple Silicon
Who it’s for. Developers and researchers who need a 7.5B parameter model with built‑in reasoning and tool‑calling capabilities. The model is suitable for local deployment on Apple Silicon and other platforms that support GGUF.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → | |
| F16 | 15.1 GB | 17.0 GB | Too big | Get file → |
For 8k context, the Q4_K_M quant uses 5.34 GB file size and requires approximately 7.2 GB of memory. The F16 quant uses 15.05 GB file size and requires approximately 17 GB of memory. Choose Q4_K_M for lower memory budgets and F16 for higher precision needs.
What GPU do you need for gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI?
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 Q4_K_M (5.3 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (5.3 GB file, about 7.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (5.3 GB file, about 7.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.1 GB file, about 17.0 GB in use).
Which gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI quant should you choose?
Q4_K_M is the usual starting point for gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI: it balances file size and quality well. Here it is a 5.3 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI
How much VRAM does gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI need?
About 7.2 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 4 E4B Agentic Sol Fable Reasoning GeminiCLI on an 8 GB GPU?
Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI GGUF?
It depends on the quant: Q4_K_M is 5.3 GB, F16 is 15.1 GB.
What context length does gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download gemma 4 E4B Agentic Sol Fable Reasoning GeminiCLI GGUF?
The files are on Hugging Face in the deadbydawn101/gemma-4-E4B-Agentic-Sol-Fable-Reasoning-GeminiCLI-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 4 E4B Agentic Sol Fable Reasoning GeminiCLI 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 this model on 8 GB VRAM?
The Q4_K_M quant requires about 7.2 GB of memory at 8k context, so it can fit in 8 GB VRAM with little headroom. The F16 quant needs about 17 GB and would not fit.
Does this model support vision?
No, the model does not include vision capabilities.
What context length does it support?
It supports up to 131072 tokens of context.