QW

Qwen 3.5 28B A3B REAP

QwenGGUF by mradermacherUpdated 2026-07-07
Download on Hugging Face
Parameters28.2B
Context256K
Layers40
Architectureqwen35moe
Smallest quant0.2 GB
Quick answer

Qwen 3.5 28B A3B 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.

Qwen 3.5 28B A3B REAP – 20% expert‑pruned Qwen3.5‑35B‑A3B

Qwen 3.5 28B A3B REAP is a 28.2B‑parameter model pruned to 80% of its original experts. It supports reasoning and tool usage and retains a 262144‑token context window. The model is released under the apache‑2.0 license.

Good at

  • Reasoning
  • Tool usage
  • Large context

Limits

  • No vision support
  • Requires at least 8 k context for memory estimates
  • License is apache‑2.0

Best for

  • Chatbots needing long context
  • Code generation with reasoning
  • Tool‑integrated workflows

Who it’s for. Developers building chat or code assistants that require a large context window and reasoning capabilities. The model is suitable for users who can run GGUF files with llama.cpp or vLLM and have access to GPUs with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.3 GB
Fits Get file →
IQ1_S6.2 GB 7.4 GB
Tight Get file →
IQ1_M6.8 GB 8.0 GB
Tight Get file →
IQ2_XXS7.8 GB 9.0 GB
Too big Get file →
IQ2_XS8.6 GB 9.8 GB
Too big Get file →
IQ2_S8.8 GB 9.9 GB
Too big Get file →
IQ2_M9.6 GB 10.7 GB
Too big Get file →
Q2_K_S10.0 GB 11.1 GB
Too big Get file →
Q2_K10.6 GB 11.8 GB
Too big Get file →
IQ3_XXS11.2 GB 12.3 GB
Too big Get file →
IQ3_XS11.9 GB 13.0 GB
Too big Get file →
Q3_K_S12.4 GB 13.6 GB
Too big Get file →
IQ3_S12.5 GB 13.6 GB
Too big Get file →
IQ3_M12.6 GB 13.8 GB
Too big Get file →
Q3_K_M13.7 GB 14.9 GB
Too big Get file →
Q3_K_L14.8 GB 16.0 GB
Too big Get file →
IQ4_XS15.3 GB 16.5 GB
Too big Get file →
Q4_016.2 GB 17.3 GB
Too big Get file →
Q4_K_S16.2 GB 17.4 GB
Too big Get file →
Q4_K_M17.3 GB 18.4 GB
Too big Get file →
Q4_117.8 GB 19.0 GB
Too big Get file →
Q5_K_S19.6 GB 20.7 GB
Too big Get file →
Q5_K_M20.2 GB 21.3 GB
Too big Get file →
Q6_K23.2 GB 24.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.19 GB, 7.4 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (8.63 GB, 9.8 GB memory). For 16 GB VRAM, Q4_K_S (16.23 GB, 17.4 GB memory). Estimates are approximate.

What GPU do you need for Qwen 3.5 28B 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 (0.2 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 Qwen 3.5 28B A3B REAP quant should you choose?

Q4_K_M is the usual starting point for Qwen 3.5 28B A3B 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

Architectureqwen35moe
Parameters28.2B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)801
Last updated2026-07-07

Frequently asked questions about Qwen 3.5 28B A3B REAP

How much VRAM does Qwen 3.5 28B A3B 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 Qwen 3.5 28B A3B 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 Qwen 3.5 28B A3B 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 Qwen 3.5 28B 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 Qwen 3.5 28B A3B REAP GGUF?

The files are on Hugging Face in the mradermacher/Qwen-3.5-28B-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.

What license does Qwen 3.5 28B A3B 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 Qwen 3.5 28B A3B REAP on 8 GB VRAM?

Yes, using the IQ1_S quant which is 6.19 GB and requires about 7.4 GB of VRAM at 8k context.

Does this model support vision?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3.5-28B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →