Qwen3.5 Creative 19B A3B REAP needs about 12.5 GB of memory at Q4_K_M (a 11.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 0.1 GB to 15.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.5 Creative 19B A3B REAP – a creative‑writing‑optimized, 19B‑parameter model with 3.0B active experts.
This model is a 19B‑parameter Qwen variant pruned with REAP to improve creative writing. It retains 3.0B active experts and supports a 262,144‑token context. The model is available in multiple GGUF quantizations optimized for creative prose.
Good at
- Creative prose and dialogue
- Worldbuilding and character work
- Stable chain‑of‑thought with a prompt nudge
Limits
- No vision support
- Requires at least 5.2GB VRAM for the smallest quant
- License terms are inherited from the base model
Best for
- Short story generation
- Dialogue scripting
- Worldbuilding prompts
Who it’s for. Developers and writers who need a lightweight creative‑writing model that fits on a 16‑24GB GPU. It is also suitable for local deployment with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.3 GB | Fits | Get file → | |
| IQ1_S | 4.1 GB | 5.2 GB | Fits | Get file → | |
| IQ1_M | 4.5 GB | 5.6 GB | Fits | Get file → | |
| IQ2_XXS | 5.1 GB | 6.3 GB | Fits | Get file → | |
| IQ2_XS | 5.7 GB | 6.8 GB | Fits | Get file → | |
| IQ2_S | 5.8 GB | 6.9 GB | Fits | Get file → | |
| IQ2_M | 6.3 GB | 7.5 GB | Tight | Get file → | |
| Q2_K_S | 6.6 GB | 7.7 GB | Tight | Get file → | |
| Q2_K | 6.9 GB | 8.1 GB | Too big | Get file → | |
| IQ3_XXS | 7.3 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XS | 7.8 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_S | 8.2 GB | 9.4 GB | Too big | Get file → | |
| IQ3_S | 8.2 GB | 9.4 GB | Too big | Get file → | |
| IQ3_M | 8.4 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_M | 9.1 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_L | 9.7 GB | 10.9 GB | Too big | Get file → | |
| IQ4_XS | 10.1 GB | 11.2 GB | Too big | Get file → | |
| IQ4_NL | 10.6 GB | 11.8 GB | Too big | Get file → | |
| Q4_0 | 10.7 GB | 11.8 GB | Too big | Get file → | |
| Q4_K_S | 10.7 GB | 11.9 GB | Too big | Get file → | |
| Q4_K_M | 11.4 GB | 12.5 GB | Too big | Get file → | |
| Q4_1 | 11.7 GB | 12.9 GB | Too big | Get file → | |
| Q5_K_S | 12.9 GB | 14.0 GB | Too big | Get file → | |
| Q5_K_M | 13.3 GB | 14.5 GB | Too big | Get file → | |
| Q6_K | 15.3 GB | 16.4 GB | Too big | Get file → |
For 16‑24GB VRAM, use the Q4_K_M quant (~12GB file, ~12.5GB memory at 8k context). If you have 8GB VRAM, the smallest usable quant is IQ1_S (~4.06GB file, ~5.2GB memory). For higher quality and more VRAM, consider Q6_K (~15.26GB file, ~16.4GB memory).
What GPU do you need for Qwen3.5 Creative 19B 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 IQ1_M (4.5 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_S (6.6 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_S (10.7 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (13.3 GB file, about 14.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (15.3 GB file, about 16.4 GB in use).
Which Qwen3.5 Creative 19B A3B REAP quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 Creative 19B A3B REAP: it balances file size and quality well. Here it is a 11.4 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 19B A3B REAP
How much VRAM does Qwen3.5 Creative 19B A3B REAP need?
About 12.5 GB at Q4_K_M with an 8K context window. That is the 11.4 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 19B A3B REAP on an 8 GB GPU?
Yes, with Q2_K_S: the 6.6 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 Creative 19B A3B REAP GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 4.1 GB, IQ1_M is 4.5 GB, IQ2_XXS is 5.1 GB, IQ2_XS is 5.7 GB, IQ2_S is 5.8 GB and 19 more.
What context length does Qwen3.5 Creative 19B 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 19B A3B REAP GGUF?
The files are on Hugging Face in the mradermacher/Qwen3.5-Creative-19B-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 this model on 8GB VRAM?
The smallest quant, IQ1_S, requires about 5.2GB memory at 8k context, so 8GB VRAM is sufficient but leaves little headroom.
Does this model support vision tasks?
No, the model has no vision capabilities.
What is the context length of this model?
It supports up to 262,144 tokens.