Gemmable 4 12B MTP needs about 1.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.3 GB (Q4_K_M) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Gemma 4 12B fine‑tuned for reasoning and assistant workflows
Gemmable 4 12B is a GGUF export of Gemma 4 12B fine‑tuned on Fable‑5 style reasoning and assistant traces. It supports local inference with llama.cpp or LM Studio and includes quantized variants for memory efficiency.
Good at
- Reasoning tasks
- Assistant style dialogue
- Local inference
Limits
- Requires paired main and mtp files
- MTP support depends on client
- No vision capability
Best for
- Coding assistance
- Complex reasoning prompts
- Local chatbot deployment
Who it’s for. Developers and researchers who need a fine‑tuned Gemma model for local inference. The model is ideal for applications requiring reasoning and assistant‑style interactions without external API calls.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 0.4 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 2.0 GB | Fits | Get file → | |
| — | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 7.4 GB | 9.0 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 11.4 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (0.33 GB) or Q6_K (0.36 GB). For 12 GB VRAM, Q8_0 (0.47 GB) is suitable. Larger memory budgets can use the 7–13 GB quantized files for higher precision.
What GPU do you need for Gemmable 4 12B MTP?
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 the main file (0.9 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 2.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 2.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.2 GB in use).
Which Gemmable 4 12B MTP quant should you choose?
Q4_K_M is the usual starting point for Gemmable 4 12B MTP: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.5 GB, about 1.4 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemmable 4 12B MTP
How much VRAM does Gemmable 4 12B MTP need?
About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 Gemmable 4 12B MTP on an 8 GB GPU?
Yes, with the smaller files: the 0.9 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemmable 4 12B MTP GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, Q6_K is 0.4 GB, Q8_0 is 0.5 GB, file is 0.9 GB, Q4_K_M is 7.4 GB, Q6_K is 9.8 GB and 1 more.
What context length does Gemmable 4 12B MTP support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Gemmable 4 12B MTP GGUF?
The files are on Hugging Face in the Mia-AiLab/Gemmable-4-12B-MTP-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 Gemmable 4 12B MTP use?
Hugging Face lists the license as apache-2.0. 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 Gemmable 4 12B on 8 GB VRAM?
Yes, the Q4_K_M or Q6_K quantized files fit within 8 GB VRAM with estimated 1.9 GB usage at 8k context.
Does this model support vision?
No, the model has no vision capability.
What license applies?
The model is released under the Apache‑2.0 license.