gemma 4 26B A4B it 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 5 quants, from 0.3 GB (Q2_K) to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Gemma 4 26B A4B it MTP – instruction‑tuned 26B model with speculative decoding
Gemma 4 26B A4B it MTP is a 26‑billion‑parameter instruction‑tuned model from Google DeepMind. It supports a 256K token context window and is packaged for llama.cpp and LM Studio with a draft‑MTP drafter. The model is released under Apache‑2.0.
Good at
- Large‑context reasoning
- Instruction following
- Multimodal text handling
Limits
- No vision or audio support in this variant
- Requires custom llama.cpp build for MTP
- Large VRAM needed for full context
Best for
- Chatbots needing long context
- Coding assistants with instruction tuning
- Agentic workflows with speculative decoding
Who it’s for. Developers and researchers who need a high‑capacity instruction‑tuned model for local deployment. The model is suitable for environments with sufficient GPU memory and a custom llama.cpp runtime that supports MTP.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.3 GB | 1.9 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 2.0 GB | Fits | Get file → | |
| F16 | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q8_0 | 26.9 GB | 28.4 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (0.29 GB file, ~1.9 GB VRAM). For 16 GB VRAM use Q4_K_M (0.33 GB file, ~1.9 GB VRAM). For 32 GB VRAM use Q8_0 (0.46 GB file, ~2 GB VRAM). Larger VRAM allows the 26.86 GB Q8_0 file for full precision.
What GPU do you need for gemma 4 26B A4B it 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 F16 (0.9 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (0.9 GB file, about 2.4 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (0.9 GB file, about 2.4 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (0.9 GB file, about 2.4 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (0.9 GB file, about 2.4 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (0.9 GB file, about 2.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 28.4 GB in use).
Which gemma 4 26B A4B it MTP quant should you choose?
Q4_K_M is the usual starting point for gemma 4 26B A4B it 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.
If memory is tight, the smallest file is Q2_K at 0.3 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 26B A4B it MTP
How much VRAM does gemma 4 26B A4B it 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 gemma 4 26B A4B it MTP on an 8 GB GPU?
Yes, with F16: 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 gemma 4 26B A4B it MTP GGUF?
It depends on the quant: Q2_K is 0.3 GB, Q4_K_M is 0.3 GB, Q8_0 is 0.5 GB, F16 is 0.9 GB, Q8_0 is 26.9 GB.
What context length does gemma 4 26B A4B it 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 gemma 4 26B A4B it MTP GGUF?
The files are on Hugging Face in the ironbcc/gemma-4-26B-A4B-it-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 gemma 4 26B A4B it 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 Gemma 4 26B A4B it MTP on 8 GB VRAM?
Use the Q2_K quantized file; it requires about 1.9 GB VRAM at 8K context.
Does this model support image input?
No, the instruction‑tuned variant does not include vision support.
What license applies to this model?
The model is released under the Apache‑2.0 license.