QW

Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B

QwenGGUF by mradermacherUpdated 2025-07-21
Download on Hugging Face
Parameters19B
Context32K
Layers28
Architectureqwen2moe
Smallest quant4.2 GB
Quick answer

Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B needs about 12.6 GB of memory at Q4_K_M (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 23 quants, from 4.2 GB (IQ1_S) to 15.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Qwen2.5 2X7B Coder – 19B parameters, 32K context, coding focus

Qwen2.5 2X7B Coder is a 19B parameter model with a 32768 token context window. It is optimized for coding tasks and supports multiple quantization formats. The model is released under the apache-2.0 license.

Good at

  • Large code generation
  • Complex coding queries
  • Multi‑language support

Limits

  • No vision capability
  • Requires large VRAM for higher quants
  • Limited to coding tasks

Best for

  • Writing boilerplate code
  • Debugging scripts
  • Explaining code snippets

Who it’s for. Developers and researchers needing a high‑capacity coding model. The model is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.2 GB 5.1 GB
Fits Get file →
IQ1_M4.6 GB 5.5 GB
Fits Get file →
IQ2_XXS5.2 GB 6.2 GB
Fits Get file →
IQ2_XS5.8 GB 6.7 GB
Fits Get file →
IQ2_S5.9 GB 6.9 GB
Fits Get file →
IQ2_M6.4 GB 7.4 GB
Tight Get file →
Q2_K_S6.7 GB 7.6 GB
Tight Get file →
Q2_K7.1 GB 8.1 GB
Too big Get file →
IQ3_XXS7.5 GB 8.5 GB
Too big Get file →
IQ3_XS8.0 GB 9.0 GB
Too big Get file →
Q3_K_S8.4 GB 9.4 GB
Too big Get file →
IQ3_S8.4 GB 9.4 GB
Too big Get file →
IQ3_M8.5 GB 9.5 GB
Too big Get file →
Q3_K_M9.2 GB 10.2 GB
Too big Get file →
Q3_K_L10.0 GB 10.9 GB
Too big Get file →
IQ4_XS10.3 GB 11.2 GB
Too big Get file →
Q4_010.9 GB 11.9 GB
Too big Get file →
Q4_K_S10.9 GB 11.9 GB
Too big Get file →
Q4_K_M11.6 GB 12.6 GB
Too big Get file →
Q4_112.0 GB 13.0 GB
Too big Get file →
Q5_K_S13.2 GB 14.1 GB
Too big Get file →
Q5_K_M13.5 GB 14.5 GB
Too big Get file →
Q6_K15.6 GB 16.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.15 GB, 5.1 GB memory at 8K context) or IQ1_M (4.55 GB, 5.5 GB). If 12 GB VRAM is available, Q4_K_M (11.59 GB, 12.6 GB) offers a good balance of size and performance. Higher quants such as Q5_K_M (13.54 GB, 14.5 GB) require more memory but provide better quality.

What GPU do you need for Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B?

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: the best quant that fits is IQ1_M (4.6 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K_S (6.7 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (10.9 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (13.5 GB file, about 14.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (15.6 GB file, about 16.6 GB in use).

Which Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B: it balances file size and quality well. Here it is a 11.6 GB file.

If memory is tight, the smallest file is IQ1_S at 4.2 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

Architectureqwen2moe
Parameters19B (approximate, mixture of experts)
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,808
Last updated2025-07-21

Frequently asked questions about Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B

How much VRAM does Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B need?

About 12.6 GB at Q4_K_M with an 8K context window. That is the 11.6 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 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B on an 8 GB GPU?

Yes, with Q2_K_S: the 6.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B GGUF?

It depends on the quant: IQ1_S is 4.2 GB, IQ1_M is 4.6 GB, IQ2_XXS is 5.2 GB, IQ2_XS is 5.8 GB, IQ2_S is 5.9 GB, IQ2_M is 6.4 GB and 17 more.

What context length does Qwen2.5 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B GGUF?

The files are on Hugging Face in the mradermacher/Qwen2.5-2X7B-Coder-VisCoder-Coder-Instruct-OlympicCoder-19B-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 2X7B Coder VisCoder Coder Instruct OlympicCoder 19B 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 IQ1_S or IQ1_M quant files, which fit within 8 GB VRAM and use about 5–5.5 GB memory at 8K context.

Does this model support image input?

No, the model has no vision capability and is focused solely on text and code.

What license applies to this model?

The model is released under the apache-2.0 license, allowing free use and modification.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →