QW

Qwen3 Coder Next REAP 40B A3B

QwenGGUF by mradermacherUpdated 2026-02-14
Download on Hugging Face
Parameters41B
Context256K
Layers48
Architectureqwen3next
Smallest quant0.2 GB
Quick answer

Qwen3 Coder Next REAP 40B A3B needs about 26.3 GB of memory at Q4_K_M (a 25.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.2 GB to 33.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 Coder Next REAP 40B A3B – 40B causal LLM with 3B active experts

Qwen3 Coder Next REAP 40B A3B is a 40B parameter causal language model with 3B activated parameters. It uses a 48‑layer architecture, 2048 hidden dimension, and a 262,144 token context length. The model is licensed under apache‑2.0.

Good at

  • Large context generation
  • Expert‑level coding
  • Long‑form text completion

Limits

  • No vision support
  • Requires large VRAM for full precision
  • Mixture of experts limits real‑time inference on low‑end GPUs

Best for

  • Code generation in IDEs
  • Long‑form documentation writing
  • Complex algorithm explanation

Who it’s for. Developers and researchers needing a large‑context code assistant. The model is suitable for environments where 3B active experts can be accommodated and where the apache‑2.0 license is acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.5 GB
Fits Get file →
IQ1_S8.4 GB 9.7 GB
Too big Get file →
IQ1_M9.4 GB 10.7 GB
Too big Get file →
IQ2_XXS10.9 GB 12.2 GB
Too big Get file →
IQ2_XS12.1 GB 13.4 GB
Too big Get file →
IQ2_S12.3 GB 13.6 GB
Too big Get file →
IQ2_M13.5 GB 14.8 GB
Too big Get file →
Q2_K_S14.1 GB 15.4 GB
Too big Get file →
Q2_K15.0 GB 16.3 GB
Too big Get file →
IQ3_XXS15.9 GB 17.2 GB
Too big Get file →
IQ3_XS16.9 GB 18.2 GB
Too big Get file →
Q3_K_S17.8 GB 19.1 GB
Too big Get file →
IQ3_S17.8 GB 19.1 GB
Too big Get file →
IQ3_M18.1 GB 19.5 GB
Too big Get file →
Q3_K_M19.8 GB 21.1 GB
Too big Get file →
Q3_K_L21.3 GB 22.6 GB
Too big Get file →
IQ4_XS22.0 GB 23.3 GB
Too big Get file →
Q4_023.3 GB 24.6 GB
Too big Get file →
Q4_K_S23.4 GB 24.7 GB
Too big Get file →
Q4_K_M25.0 GB 26.3 GB
Too big Get file →
Q4_125.8 GB 27.1 GB
Too big Get file →
Q5_K_S28.3 GB 29.6 GB
Too big Get file →
Q5_K_M29.3 GB 30.6 GB
Too big Get file →
Q6_K33.7 GB 35.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (8.43 GB file, 9.7 GB memory at 8k context). For 16 GB VRAM, IQ2_S (12.13 GB file, 13.4 GB memory) or Q2_K_S (14.09 GB file, 15.4 GB memory). For 24 GB VRAM, Q4_K_M (24.98 GB file, 26.3 GB memory) is a good balance between size and performance. Memory estimates are approximate.

What GPU do you need for Qwen3 Coder Next REAP 40B 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: the best quant that fits is the main file (0.2 GB file, about 1.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.5 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (9.4 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K_S (14.1 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (22.0 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (29.3 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (33.7 GB file, about 35.0 GB in use).

Which Qwen3 Coder Next REAP 40B A3B quant should you choose?

Q4_K_M is the usual starting point for Qwen3 Coder Next REAP 40B A3B: it balances file size and quality well. Here it is a 25.0 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

Architectureqwen3next
Parameters41B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,742
Last updated2026-02-14

Frequently asked questions about Qwen3 Coder Next REAP 40B A3B

How much VRAM does Qwen3 Coder Next REAP 40B A3B need?

About 26.3 GB at Q4_K_M with an 8K context window. That is the 25.0 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 Coder Next REAP 40B A3B on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 Coder Next REAP 40B A3B GGUF?

It depends on the quant: file is 0.2 GB, IQ1_S is 8.4 GB, IQ1_M is 9.4 GB, IQ2_XXS is 10.9 GB, IQ2_XS is 12.1 GB, IQ2_S is 12.3 GB and 18 more.

What context length does Qwen3 Coder Next REAP 40B 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 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Qwen3 Coder Next REAP 40B A3B GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-Coder-Next-REAP-40B-A3B-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 Coder Next REAP 40B 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 Qwen3 Coder Next REAP 40B A3B on 8 GB VRAM?

The smallest quant for 8 GB VRAM is IQ1_S, which requires 9.7 GB memory at 8k context, so it will not fit. A larger VRAM or lower‑precision quant is needed.

Does this model support image input?

No, the model is a causal language model and has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3-Coder-Next-REAP-40B-A3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →