Gemma 4 A4B 109e v3 It needs about 23.1 GB of memory at Q4_K_M (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 9.2 GB (Q2_K) to 23.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma 4 A4B 109e v3 It – 21.8B parameter LLM with vision, reasoning, and tools
Gemma 4 A4B 109e v3 It is a 21.8B parameter model with 4B active parameters in a mixture of experts. It supports reasoning, tools, and vision tasks. The model is available in multiple GGUF quantizations.
Good at
- Reasoning and logic tasks
- Tool use and API integration
- Vision‑enabled prompts
Limits
- Requires large VRAM for higher quants
- No explicit language support list
- License is gemma
Best for
- Complex question answering
- Automated code generation with tool calls
- Image captioning and analysis
Who it’s for. Developers building AI assistants that need reasoning, tool use, and vision in a single model. Researchers exploring mixture‑of‑experts architectures may also find it useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 9.2 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_S | 10.6 GB | 19.2 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 20.1 GB | Too big | Get file → | |
| Q3_K_L | 12.0 GB | 20.6 GB | Too big | Get file → | |
| IQ4_XS | 12.2 GB | 20.8 GB | Too big | Get file → | |
| Q4_K_S | 13.4 GB | 22.0 GB | Too big | Get file → | |
| Q4_K_M | 14.5 GB | 23.1 GB | Too big | Get file → | |
| Q5_K_S | 15.6 GB | 24.1 GB | Too big | Get file → | |
| Q5_K_M | 16.6 GB | 25.1 GB | Too big | Get file → | |
| Q6_K | 19.6 GB | 28.1 GB | Too big | Get file → | |
| Q8_0 | 23.3 GB | 31.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 9.2 GB, estimated 17.8 GB memory). For 12 GB VRAM, Q3_K_S (10.61 GB, 19.2 GB memory) or Q3_K_M (11.53 GB, 20.1 GB memory). For 16 GB VRAM, Q4_K_S (13.4 GB, 22 GB memory) or Q4_K_M (14.54 GB, 23.1 GB memory).
What GPU do you need for Gemma 4 A4B 109e v3 It?
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: the best quant that fits is Q4_K_M (14.5 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (23.3 GB file, about 31.8 GB in use).
Which Gemma 4 A4B 109e v3 It quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 A4B 109e v3 It: it balances file size and quality well. Here it is a 14.5 GB file.
The Q8_0 file is 23.3 GB, about 1.6 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 9.2 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
Source
Frequently asked questions about Gemma 4 A4B 109e v3 It
How much VRAM does Gemma 4 A4B 109e v3 It need?
About 23.1 GB at Q4_K_M with an 8K context window. That is the 14.5 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 Gemma 4 A4B 109e v3 It on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 A4B 109e v3 It GGUF?
It depends on the quant: Q2_K is 9.2 GB, Q3_K_S is 10.6 GB, Q3_K_M is 11.5 GB, Q3_K_L is 12.0 GB, IQ4_XS is 12.2 GB, Q4_K_S is 13.4 GB and 5 more.
What context length does Gemma 4 A4B 109e v3 It 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 Gemma 4 A4B 109e v3 It GGUF?
The files are on Hugging Face in the mradermacher/gemma-4-A4B-109e-v3-it-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 A4B 109e v3 It 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 4 A4B 109e v3 It on 8 GB VRAM?
Use the Q2_K quant; it requires about 17.8 GB of VRAM at 8 k context, so 8 GB is insufficient. Consider a lower‑precision quant or more VRAM.
Does this model support vision tasks?
Yes, the model has detected vision ability and can process image inputs.
What license applies to this model?
The model is licensed under the gemma license.