GE

GemPT 26B A4B

GemptGGUF by mradermacherUpdated 2026-10-31
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant10.6 GB
Quick answer

GemPT 26B A4B 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. This repository has 11 quants, from 10.6 GB (Q2_K) to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

GemPT 26B A4B – a 25.2B‑parameter gemma4 model fine‑tuned for reasoning and vision

GemPT 26B A4B is a 25.2B‑parameter gemma4 model fine‑tuned from Gemma‑4‑26B‑A4B‑IT. It was trained on a single MI300X accelerator using LoRA and Unsloth. The model supports reasoning and vision tasks and is released under apache‑2.0.

Good at

  • Reasoning with step‑by‑step chain‑of‑thought
  • Vision inference
  • Large context up to 262144 tokens

Limits

  • No vision support on CPU-only setups
  • Requires at least 8k context for full performance
  • License is apache‑2.0

Best for

  • Chatbots needing deep reasoning
  • Image‑captioning pipelines
  • Long‑form document analysis

Who it’s for. Developers building AI assistants that require advanced reasoning and vision capabilities. Researchers looking for a large gemma4 model with fine‑tuned chain‑of‑thought behavior.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.6 GB 19.1 GB
Too big Get file →
Q3_K_S12.2 GB 20.8 GB
Too big Get file →
Q3_K_M13.3 GB 21.8 GB
Too big Get file →
Q3_K_L13.8 GB 22.4 GB
Too big Get file →
IQ4_XS14.1 GB 22.6 GB
Too big Get file →
Q4_K_S15.5 GB 24.0 GB
Too big Get file →
Q4_K_M16.8 GB 25.3 GB
Too big Get file →
Q5_K_S18.0 GB 26.5 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q6_K22.6 GB 31.2 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →

For 8 GB VRAM use Q2_K (10.58 GB, 19.1 GB memory at 8k context). For 16 GB VRAM Q4_K_M (16.8 GB, 25.3 GB memory) or Q5_K_M (19.13 GB, 27.7 GB memory). For 24 GB VRAM Q6_K (22.64 GB, 31.2 GB memory) or Q8_0 (26.86 GB, 35.4 GB memory). Estimates are approximate.

What GPU do you need for GemPT 26B A4B?

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_S (15.5 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).

Which GemPT 26B A4B quant should you choose?

Q4_K_M is the usual starting point for GemPT 26B A4B: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 26.9 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 10.6 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

Architecturegemma4
Parameters25.2B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymradermacher
FamilyGempt
Licenseapache-2.0
Downloads (HF)761
Last updated2026-10-31

Frequently asked questions about GemPT 26B A4B

How much VRAM does GemPT 26B A4B 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 GemPT 26B A4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GemPT 26B A4B GGUF?

It depends on the quant: Q2_K is 10.6 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.3 GB, Q3_K_L is 13.8 GB, IQ4_XS is 14.1 GB, Q4_K_S is 15.5 GB and 5 more.

What context length does GemPT 26B A4B 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 GemPT 26B A4B GGUF?

The files are on Hugging Face in the mradermacher/GemPT-26B-A4B-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 GemPT 26B A4B 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 GemPT 26B A4B on 8 GB VRAM?

Use the Q2_K quant which is 10.58 GB and requires about 19.1 GB memory at 8k context. It will fit on 8 GB VRAM with swapping.

Does GemPT 26B A4B support vision tasks?

Yes, the model has detected vision ability, but it may need GPU support for efficient inference.

Other GGUFs of GemPT-26B-A4B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gempt models

All Gempt →

Other medium models

All medium models →