QW

cerebras/Qwen3-Coder-REAP-25B-A3B

QwenGGUF by csabakecskemetiUpdated 2025-10-22
Download on Hugging Face
Parameters24.9B
Context256K
Layers48
Architectureqwen3moe
Smallest quant9.2 GB
Quick answer

cerebras/Qwen3-Coder-REAP-25B-A3B 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 11 quants, from 9.2 GB (Q2_K) to 49.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Memory‑efficient Qwen3 coder model with 25B parameters and 3B active experts

Qwen3-Coder-REAP-25B-A3B is a sparse Mixture‑of‑Experts causal language model. It contains 25B total parameters, 3B activated per token, and supports a native context length of 262,144 tokens. The model is released under Apache 2.0.

Good at

  • Code generation
  • Agentic coding
  • Function calling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Local code assistant
  • Repository‑scale code analysis
  • Function‑calling agents

Who it’s for. Developers and researchers needing a lightweight code model that retains full coding capabilities. It is suitable for local deployments and academic projects where memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K9.2 GB 10.5 GB
Too big Get file →
Q3_K_S10.8 GB 12.2 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 →
Q4_K_S14.2 GB 15.5 GB
Too big Get file →
Q4_K_M15.1 GB 16.4 GB
Too big Get file →
Q5_K_S17.2 GB 18.5 GB
Too big Get file →
Q5_K_M17.7 GB 19.0 GB
Too big Get file →
Q6_K20.4 GB 21.7 GB
Too big Get file →
Q8_026.5 GB 27.8 GB
Too big Get file →
F1649.8 GB (2 parts) 51.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 14.23 GB, estimated 15.5 GB memory at 8k context). For 12 GB VRAM, Q5_K_S (17.18 GB, 18.5 GB memory) is a good balance. Higher quants such as Q6_K or Q8_0 require more than 20 GB VRAM.

What GPU do you need for cerebras/Qwen3-Coder-REAP-25B-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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q2_K (9.2 GB file, about 10.5 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 Q6_K (20.4 GB file, about 21.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (26.5 GB file, about 27.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.5 GB file, about 27.8 GB in use).

Which cerebras/Qwen3-Coder-REAP-25B-A3B quant should you choose?

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

The Q8_0 file is 26.5 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 9.2 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
Parameters24.9B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bycsabakecskemeti
FamilyQwen
Licenseapache-2.0
Downloads (HF)923
Last updated2025-10-22

Frequently asked questions about cerebras/Qwen3-Coder-REAP-25B-A3B

How much VRAM does cerebras/Qwen3-Coder-REAP-25B-A3B 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 cerebras/Qwen3-Coder-REAP-25B-A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cerebras/Qwen3-Coder-REAP-25B-A3B GGUF?

It depends on the quant: Q2_K is 9.2 GB, Q3_K_S is 10.8 GB, Q3_K_M is 12.0 GB, Q3_K_L is 13.0 GB, Q4_K_S is 14.2 GB, Q4_K_M is 15.1 GB and 5 more.

What context length does cerebras/Qwen3-Coder-REAP-25B-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 cerebras/Qwen3-Coder-REAP-25B-A3B GGUF?

The files are on Hugging Face in the csabakecskemeti/cerebras.Qwen3-Coder-REAP-25B-A3B-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 cerebras/Qwen3-Coder-REAP-25B-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-REAP-25B-A3B on 8 GB VRAM?

Use the Q4_K_S quant, which estimates 15.5 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.

Does this model support image inputs?

No, the model 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-REAP-25B-A3B

Similar models

Browse all →

More from csabakecskemeti

All by csabakecskemeti →

More Qwen models

All Qwen →

Other medium models

All medium models →