Whittle Next 27B A3B needs about 18.0 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.3 GB (Q2_K) to 29.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Whittle Next 27B A3B – a Qwen4exp model with 27.6B parameters and 3B active experts
Whittle Next 27B A3B is a 27.6B‑parameter Qwen4exp model with a 3B‑parameter mixture of experts. It was trained on 262,144 context tokens and is available in multiple GGUF quantizations. The model supports coding, embedding, reasoning and tool use.
Good at
- Coding tasks
- Embedding generation
- Reasoning with tools
Limits
- No vision support
- Requires large VRAM for higher‑quality quants
- Apache‑2.0 license
Best for
- Developers building custom LLMs
- Researchers experimenting with Qwen4exp architecture
- Users needing a large‑parameter model for code analysis
Who it’s for. This model is intended for researchers and developers who want a starting point for building on the Qwen4‑Next architecture. It is not a finished general‑purpose model and should be used as a baseline for further training or fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.3 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_S | 12.2 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 14.5 GB | Too big | Get file → | |
| Q3_K_L | 14.3 GB | 15.5 GB | Too big | Get file → | |
| IQ4_XS | 15.1 GB | 16.3 GB | Too big | Get file → | |
| Q4_K_S | 15.9 GB | 17.0 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 18.0 GB | Too big | Get file → | |
| Q5_K_S | 19.1 GB | 20.3 GB | Too big | Get file → | |
| Q5_K_M | 19.6 GB | 20.8 GB | Too big | Get file → | |
| Q6_K | 22.7 GB | 23.9 GB | Too big | Get file → | |
| Q8_0 | 29.3 GB | 30.5 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 16.8 GB, estimated memory 18 GB). For 12 GB VRAM use Q5_K_S (file size 19.11 GB, estimated memory 20.3 GB). For 16 GB VRAM use Q6_K (file size 22.73 GB, estimated memory 23.9 GB).
What GPU do you need for Whittle Next 27B 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: the best quant that fits is Q2_K (10.3 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (14.3 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (22.7 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.3 GB file, about 30.5 GB in use).
Which Whittle Next 27B A3B quant should you choose?
Q4_K_M is the usual starting point for Whittle Next 27B A3B: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 29.3 GB, about 1.7 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 10.3 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 Whittle Next 27B A3B
How much VRAM does Whittle Next 27B A3B need?
About 18.0 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 Whittle Next 27B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Whittle Next 27B A3B GGUF?
It depends on the quant: Q2_K is 10.3 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.1 GB, Q4_K_S is 15.9 GB and 5 more.
What context length does Whittle Next 27B 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 27B A3B GGUF?
The files are on Hugging Face in the mradermacher/Whittle-Next-27B-A3B-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 Whittle Next 27B 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 27B A3B on 8 GB VRAM?
Use the Q4_K_M quant; it requires about 18 GB of VRAM, so 8 GB is insufficient.
Does the model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.