Qwen3.6 28B REAP needs about 18.4 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.2 GB to 23.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.6 28B REAP – 28B parameter model with 20% expert pruning and Opus fine‑tuning
Qwen3.6 28B REAP is a 28.2B‑parameter model derived from Qwen3.6‑35B‑A3B. It uses 20% REAP pruning and LoRA SFT on Claude Opus reasoning traces. The model is released under Apache‑2.0 and supports 262144‑token context.
Good at
- Reasoning with chain‑of‑thought
- Structured output in JSON/Mermaid
- Large‑context dialogue
Limits
- No vision support
- Refusal behavior follows base model
- Short max‑tokens limit hurts accuracy
Best for
- Fine‑tuning for reasoning tasks
- Generating structured JSON or Mermaid diagrams
- Long‑form conversation with large context
Who it’s for. Developers needing a large‑context LLM with strong reasoning and structured‑output capabilities. The model is suitable for research and production use where Apache‑2.0 licensing is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.3 GB | Fits | Get file → | |
| IQ1_S | 6.2 GB | 7.4 GB | Tight | Get file → | |
| IQ1_M | 6.8 GB | 8.0 GB | Tight | Get file → | |
| IQ2_XXS | 7.8 GB | 9.0 GB | Too big | Get file → | |
| IQ2_XS | 8.6 GB | 9.8 GB | Too big | Get file → | |
| IQ2_S | 8.8 GB | 9.9 GB | Too big | Get file → | |
| IQ2_M | 9.6 GB | 10.7 GB | Too big | Get file → | |
| Q2_K_S | 10.0 GB | 11.1 GB | Too big | Get file → | |
| Q2_K | 10.6 GB | 11.8 GB | Too big | Get file → | |
| IQ3_XXS | 11.2 GB | 12.3 GB | Too big | Get file → | |
| IQ3_XS | 11.9 GB | 13.0 GB | Too big | Get file → | |
| Q3_K_S | 12.4 GB | 13.6 GB | Too big | Get file → | |
| IQ3_S | 12.5 GB | 13.6 GB | Too big | Get file → | |
| IQ3_M | 12.6 GB | 13.8 GB | Too big | Get file → | |
| Q3_K_M | 13.7 GB | 14.9 GB | Too big | Get file → | |
| Q3_K_L | 14.8 GB | 16.0 GB | Too big | Get file → | |
| IQ4_XS | 15.3 GB | 16.5 GB | Too big | Get file → | |
| Q4_0 | 16.2 GB | 17.3 GB | Too big | Get file → | |
| Q4_K_S | 16.2 GB | 17.4 GB | Too big | Get file → | |
| Q4_K_M | 17.3 GB | 18.4 GB | Too big | Get file → | |
| Q4_1 | 17.8 GB | 19.0 GB | Too big | Get file → | |
| Q5_K_S | 19.6 GB | 20.7 GB | Too big | Get file → | |
| Q5_K_M | 20.2 GB | 21.3 GB | Too big | Get file → | |
| Q6_K | 23.2 GB | 24.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.19 GB, 7.4 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (8.63 GB, 9.8 GB memory). For 24 GB VRAM, Q6_K (23.23 GB, 24.4 GB memory). Estimates are approximate.
What GPU do you need for Qwen3.6 28B 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 (0.2 GB file, about 1.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.3 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_M (6.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (10.6 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (14.8 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (20.2 GB file, about 21.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (23.2 GB file, about 24.4 GB in use).
Which Qwen3.6 28B REAP quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 28B REAP: it balances file size and quality well. Here it is a 17.3 GB file.
If memory is tight, the smallest file is the first one in the table at 0.2 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 Qwen3.6 28B REAP
How much VRAM does Qwen3.6 28B REAP need?
About 18.4 GB at Q4_K_M with an 8K context window. That is the 17.3 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 Qwen3.6 28B REAP on an 8 GB GPU?
Yes, with IQ1_M: the 6.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.6 28B REAP GGUF?
It depends on the quant: file is 0.2 GB, IQ1_S is 6.2 GB, IQ1_M is 6.8 GB, IQ2_XXS is 7.8 GB, IQ2_XS is 8.6 GB, IQ2_S is 8.8 GB and 18 more.
What context length does Qwen3.6 28B 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 Qwen3.6 28B REAP GGUF?
The files are on Hugging Face in the mradermacher/Qwen3.6-28B-REAP-i1-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 Qwen3.6 28B REAP 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 Qwen3.6 28B REAP on 8 GB VRAM?
Yes, the IQ1_S quant is 6.19 GB and requires about 7.4 GB memory at 8 k context.
Does the model support image input?
No, the model has no vision capability.
What license does it use?
Apache‑2.0, inherited from the base model.