QW

Qwen3 coder REAP 25B A3B Rust

QwenGGUF by Em-80Updated 2026-07-11
Download on Hugging Face
Parameters25B
Context256K
Layers48
Architectureqwen3moe
Smallest quant5.3 GB
Quick answer

Qwen3 coder REAP 25B A3B Rust needs about 16.4 GB of memory at Q4_K_M (a 15.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 5.3 GB (IQ1_S) to 18.7 GB (Q5_1). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 coder REAP 25B A3B Rust – a compressed, code‑focused LLM

Qwen3 coder REAP 25B A3B Rust is a 25B‑parameter sparse Mixture‑of‑Experts model with 3B active experts per token. It supports a native context length of 262,144 tokens and is optimized for Rust code generation. The model is released under Apache 2.0.

Good at

  • Rust code generation
  • Multi‑lingual coding
  • Mathematical reasoning

Limits

  • No vision support
  • Requires at least 8 GB VRAM for larger quants
  • Context length limited to 262,144 tokens unless extended

Best for

  • Local code generation on limited GPU
  • Academic research on sparse models
  • Deploying Rust‑focused assistants

Who it’s for. Developers and researchers needing a lightweight, code‑centric LLM that runs locally. The model is ideal for environments with constrained GPU memory and for projects focused on Rust and multi‑lingual coding tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.3 GB 6.6 GB
Fits Get file →
IQ1_M5.8 GB 7.1 GB
Fits Get file →
IQ2_XXS6.7 GB 8.0 GB
Too big Get file →
IQ2_XS7.4 GB 8.7 GB
Too big Get file →
IQ2_S7.6 GB 8.9 GB
Too big Get file →
IQ2_M8.3 GB 9.6 GB
Too big Get file →
Q2_K_S8.6 GB 9.9 GB
Too big Get file →
Q2_K9.2 GB 10.5 GB
Too big Get file →
IQ3_XXS9.7 GB 11.0 GB
Too big Get file →
IQ3_XS10.3 GB 11.6 GB
Too big Get file →
Q3_K_S10.8 GB 12.2 GB
Too big Get file →
IQ3_S10.9 GB 12.2 GB
Too big Get file →
IQ3_M11.0 GB 12.3 GB
Too big Get file →
Q3_K_M12.0 GB 13.3 GB
Too big Get file →
Q3_K_L13.0 GB 14.3 GB
Too big Get file →
IQ4_XS13.4 GB 14.7 GB
Too big Get file →
IQ4_NL14.1 GB 15.4 GB
Too big Get file →
Q4_014.2 GB 15.5 GB
Too big Get file →
Q4_K_S14.2 GB 15.5 GB
Too big Get file →
Q4_K_M15.1 GB 16.4 GB
Too big Get file →
Q4_115.6 GB 16.9 GB
Too big Get file →
Q5_K_S17.2 GB 18.5 GB
Too big Get file →
Q5_017.2 GB 18.5 GB
Too big Get file →
Q5_K_M17.7 GB 19.0 GB
Too big Get file →
Q5_118.7 GB 20.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (5.27 GB, 6.6 GB memory) or IQ1_M (5.8 GB, 7.1 GB memory). With 12 GB VRAM, Q2_K (9.2 GB, 10.5 GB memory) or Q3_K_S (10.85 GB, 12.2 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q4_K_M (15.12 GB, 16.4 GB memory).

What GPU do you need for Qwen3 coder REAP 25B A3B Rust?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ2_XXS (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XS (10.3 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (14.2 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_1 (18.7 GB file, about 20.0 GB in use).

Which Qwen3 coder REAP 25B A3B Rust quant should you choose?

Q4_K_M is the usual starting point for Qwen3 coder REAP 25B A3B Rust: it balances file size and quality well. Here it is a 15.1 GB file.

If memory is tight, the smallest file is IQ1_S at 5.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters25B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized byEm-80
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,900
Last updated2026-07-11

Frequently asked questions about Qwen3 coder REAP 25B A3B Rust

How much VRAM does Qwen3 coder REAP 25B A3B Rust need?

About 16.4 GB at Q4_K_M with an 8K context window. That is the 15.1 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 REAP 25B A3B Rust on an 8 GB GPU?

Yes, with IQ2_XXS: the 6.7 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 coder REAP 25B A3B Rust GGUF?

It depends on the quant: IQ1_S is 5.3 GB, IQ1_M is 5.8 GB, IQ2_XXS is 6.7 GB, IQ2_XS is 7.4 GB, IQ2_S is 7.6 GB, IQ2_M is 8.3 GB and 19 more.

What context length does Qwen3 coder REAP 25B A3B Rust 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 REAP 25B A3B Rust GGUF?

The files are on Hugging Face in the Em-80/Qwen3-coder-REAP-25B-A3B-Rust-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 REAP 25B A3B Rust 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 this model on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quant, which require approximately 6.6–7.1 GB memory at 8k context.

Does this model support image input?

No, the model has no vision capabilities and only processes text.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of Qwen3-Coder-REAP-25B-A3B

Similar models

Browse all →

More Qwen models

All Qwen →

Other medium models

All medium models →