Qwen3.5 Creative 26B A3B REAP needs about 17.4 GB of memory at Q4_K_M (a 16.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 21.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.5 Creative 26B A3B REAP – a 26.6B MoE model optimized for creative writing
Qwen3.5 Creative 26B A3B REAP is a 26.6B parameter model with 3B active experts. It is pruned 25% using REAP for creative writing while retaining reasoning capability. The model supports 262144 token context and is available in multiple GGUF quantizations.
Good at
- Creative storytelling
- Reasoning with tools
- Long‑form plot consistency
Limits
- No vision support
- Requires large VRAM for higher quants
- License not specified
Best for
- Writing novels
- Developing dialogue scripts
- Generating detailed narratives
Who it’s for. Developers and writers who need a balance between creative output and reasoning. Suitable for local deployment with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.3 GB | Fits | Get file → | |
| IQ1_S | 5.7 GB | 6.8 GB | Fits | Get file → | |
| IQ1_M | 6.3 GB | 7.4 GB | Tight | Get file → | |
| IQ2_XXS | 7.2 GB | 8.4 GB | Too big | Get file → | |
| IQ2_XS | 8.0 GB | 9.2 GB | Too big | Get file → | |
| IQ2_S | 8.1 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 8.9 GB | 10.1 GB | Too big | Get file → | |
| Q2_K_S | 9.3 GB | 10.5 GB | Too big | Get file → | |
| Q2_K | 9.9 GB | 11.1 GB | Too big | Get file → | |
| IQ3_XXS | 10.4 GB | 11.6 GB | Too big | Get file → | |
| IQ3_XS | 11.1 GB | 12.3 GB | Too big | Get file → | |
| Q3_K_S | 11.7 GB | 12.9 GB | Too big | Get file → | |
| IQ3_S | 11.7 GB | 12.9 GB | Too big | Get file → | |
| IQ3_M | 11.9 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_M | 12.9 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_L | 13.9 GB | 15.1 GB | Too big | Get file → | |
| IQ4_XS | 14.4 GB | 15.5 GB | Too big | Get file → | |
| Q4_0 | 15.2 GB | 16.4 GB | Too big | Get file → | |
| Q4_K_S | 15.3 GB | 16.5 GB | Too big | Get file → | |
| Q4_K_M | 16.3 GB | 17.4 GB | Too big | Get file → | |
| Q4_1 | 16.8 GB | 18.0 GB | Too big | Get file → | |
| Q5_K_S | 18.4 GB | 19.6 GB | Too big | Get file → | |
| Q5_K_M | 19.0 GB | 20.2 GB | Too big | Get file → | |
| Q6_K | 21.9 GB | 23.1 GB | Too big | Get file → |
For 24GB VRAM, use Q4_K_M (~15.29GB file, ~16.5GB memory at 8k context). If 32GB VRAM is available, Q6_K (~21.89GB file, ~23.1GB memory) offers higher quality. Lower quants such as IQ1_S (~5.68GB file, ~6.8GB memory) fit 8GB VRAM setups.
What GPU do you need for Qwen3.5 Creative 26B A3B REAP?
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 (0.1 GB file, about 1.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_M (6.3 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XXS (10.4 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (14.4 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (21.9 GB file, about 23.1 GB in use).
Which Qwen3.5 Creative 26B A3B REAP quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 Creative 26B A3B REAP: it balances file size and quality well. Here it is a 16.3 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.5 Creative 26B A3B REAP
How much VRAM does Qwen3.5 Creative 26B A3B REAP need?
About 17.4 GB at Q4_K_M with an 8K context window. That is the 16.3 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 Qwen3.5 Creative 26B A3B REAP on an 8 GB GPU?
Yes, with IQ1_M: the 6.3 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 Creative 26B A3B REAP GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 5.7 GB, IQ1_M is 6.3 GB, IQ2_XXS is 7.2 GB, IQ2_XS is 8.0 GB, IQ2_S is 8.1 GB and 18 more.
What context length does Qwen3.5 Creative 26B A3B REAP 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 Qwen3.5 Creative 26B A3B REAP GGUF?
The files are on Hugging Face in the mradermacher/Qwen3.5-Creative-26B-A3B-REAP-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Qwen3.5 Creative 26B A3B on 8GB VRAM?
Use IQ1_S or IQ1_M quant, which require approximately 6.8GB or 7.4GB memory at 8k context.
Does this model support image input?
No, the model has no vision capabilities.
What is the context length?
The model supports 262144 token context.