Whittle Next 26B A3B needs about 29.4 GB of memory at Q8_0 (a 28.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Whittle Next 26B A3B – a 26.6B Qwen4exp model in GGUF format
Whittle Next 26B A3B is a 26.6B parameter Qwen4exp model built from Qwen3.6. It is a mixture of experts with 3B active parameters and trained on 262144 context tokens. The model is available as a single Q8_0 GGUF file.
Good at
- embedding
- reasoning
- tools
Limits
- no vision support
- requires 29.4GB VRAM at 8k context
- licensed under apache-2.0
Best for
- embedding generation
- reasoning tasks
- tool‑use scenarios
Who it’s for. Developers needing a large‑parameter Qwen model for text‑only workloads. The model is suitable for research and production use where a 26B parameter size is required and the user has sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 28.3 GB | 29.4 GB | Too big | Get file → |
The only available quant is Q8_0, file size 28.27GB, requiring about 29.4GB VRAM at 8k context. This is the recommended quant for users with that memory budget. No other quants are provided.
What GPU do you need for Whittle Next 26B A3B?
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q8_0 (28.3 GB file, about 29.4 GB in use).
Which Whittle Next 26B A3B quant should you choose?
Q8_0 (28.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Whittle Next 26B A3B
How much VRAM does Whittle Next 26B A3B need?
About 29.4 GB at Q8_0 with an 8K context window. That is the 28.3 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 Whittle Next 26B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Whittle Next 26B A3B GGUF?
It depends on the quant: Q8_0 is 28.3 GB.
What context length does Whittle Next 26B A3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Whittle Next 26B A3B GGUF?
The files are on Hugging Face in the logic65/Whittle-Next-26B-A3B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Whittle Next 26B A3B 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 Whittle Next 26B A3B on 8 GB VRAM?
No. The Q8_0 quant requires about 29.4GB VRAM at 8k context, which exceeds 8 GB.
Does the model support vision tasks?
No. The model has no vision capability.
What license applies to this model?
The model is licensed under apache-2.0.