QW

Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx

QwenGGUF by mradermacherUpdated 2025-07-16
Download on Hugging Face
Parameters24.7B
Context128K
Layers28
Architectureqwen2moe
Smallest quant5.3 GB
Quick answer

Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx needs about 16.0 GB of memory at Q4_K_M (a 15.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 23 quants, from 5.3 GB (IQ1_S) to 20.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx – a large coding‑focused model

Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx is a 24.7B parameter model built on the qwen2moe architecture. It supports coding and tool usage and is trained on a 131072 token context window. The model is released under the apache-2.0 license.

Good at

  • Large‑context code generation
  • Tool‑aware programming
  • Multi‑language coding

Limits

  • Requires high VRAM for full precision
  • No vision support
  • Large context may increase memory usage

Best for

  • Complex code synthesis
  • Long‑form documentation generation
  • Debugging large codebases

Who it’s for. Developers and researchers needing a high‑capacity coding model with extended context. The model is suitable for environments that can accommodate its memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.3 GB 6.3 GB
Fits Get file →
IQ1_M5.8 GB 6.8 GB
Fits Get file →
IQ2_XXS6.7 GB 7.7 GB
Tight Get file →
IQ2_XS7.4 GB 8.4 GB
Too big Get file →
IQ2_S7.6 GB 8.6 GB
Too big Get file →
IQ2_M8.3 GB 9.3 GB
Too big Get file →
Q2_K_S8.6 GB 9.6 GB
Too big Get file →
Q2_K9.2 GB 10.2 GB
Too big Get file →
IQ3_XXS9.7 GB 10.6 GB
Too big Get file →
IQ3_XS10.3 GB 11.3 GB
Too big Get file →
Q3_K_S10.8 GB 11.8 GB
Too big Get file →
IQ3_S10.9 GB 11.8 GB
Too big Get file →
IQ3_M11.0 GB 12.0 GB
Too big Get file →
Q3_K_M11.9 GB 12.9 GB
Too big Get file →
Q3_K_L12.9 GB 13.9 GB
Too big Get file →
IQ4_XS13.3 GB 14.3 GB
Too big Get file →
Q4_014.1 GB 15.1 GB
Too big Get file →
Q4_K_S14.2 GB 15.1 GB
Too big Get file →
Q4_K_M15.0 GB 16.0 GB
Too big Get file →
Q4_115.6 GB 16.5 GB
Too big Get file →
Q5_K_S17.1 GB 18.0 GB
Too big Get file →
Q5_K_M17.6 GB 18.6 GB
Too big Get file →
Q6_K20.3 GB 21.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 5.28 GB, estimated 6.3 GB at 8k context). For 12 GB VRAM, IQ2_XXS (file size 6.7 GB, estimated 7.7 GB). For 16 GB VRAM, Q4_K_M (file size 15.04 GB, estimated 16 GB).

What GPU do you need for Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx?

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 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_M (11.0 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (15.0 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (20.3 GB file, about 21.3 GB in use).

Which Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx: it balances file size and quality well. Here it is a 15.0 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

Architectureqwen2moe
Parameters24.7B (approximate, mixture of experts)
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)729
Last updated2025-07-16

Frequently asked questions about Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx

How much VRAM does Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx need?

About 16.0 GB at Q4_K_M with an 8K context window. That is the 15.0 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 Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx on an 8 GB GPU?

Yes, with IQ2_XXS: the 6.7 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx 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 17 more.

What context length does Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx GGUF?

The files are on Hugging Face in the mradermacher/Qwen2.5-3X7B-CoderInstruct-OlympicCoder-MS-Next-Coder-25B-v1-128k-ctx-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 Qwen2.5 3X7B CoderInstruct OlympicCoder MS Next Coder 25B v1 128k Ctx 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?

Use the IQ1_S quant, which requires approximately 6.3 GB at 8k context. This fits within an 8 GB VRAM budget with some headroom.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What is the maximum context length?

The model is trained on 131072 tokens and supports up to that context length.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →