QW

Qwen2.5 6x7B Six Pack Coder Instruct 38B

QwenGGUF by mradermacherUpdated 2025-07-17
Download on Hugging Face
Parameters42B
Context32K
Layers28
Architectureqwen2moe
Smallest quant8.7 GB
Quick answer

Qwen2.5 6x7B Six Pack Coder Instruct 38B needs about 26.4 GB of memory at Q4_K_M (a 25.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 23 quants, from 8.7 GB (IQ1_S) to 34.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Qwen2.5 6x7B Six Pack Coder Instruct 38B – a large coding‑focused LLM

Qwen2.5 6x7B Six Pack Coder Instruct 38B is a 42 billion‑parameter model built on the qwen2moe architecture. It is trained on 32768 context tokens and licensed under apache‑2.0. The model is optimized for coding tasks and available in multiple GGUF quantizations.

Good at

  • Large‑context code generation
  • Complex programming logic
  • Multi‑language coding

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is apache‑2.0

Best for

  • Developers needing long‑context code assistance
  • Code review automation
  • Educational coding tools

Who it’s for. This model is suited for developers, researchers, and educators who need a powerful coding assistant with extensive context. It is ideal for projects that can accommodate the memory demands of a 42 billion‑parameter model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S8.7 GB 9.6 GB
Too big Get file →
IQ1_M9.6 GB 10.6 GB
Too big Get file →
IQ2_XXS11.1 GB 12.1 GB
Too big Get file →
IQ2_XS12.4 GB 13.4 GB
Too big Get file →
IQ2_S12.6 GB 13.6 GB
Too big Get file →
IQ2_M13.8 GB 14.8 GB
Too big Get file →
Q2_K_S14.4 GB 15.3 GB
Too big Get file →
Q2_K15.4 GB 16.4 GB
Too big Get file →
IQ3_XXS16.2 GB 17.2 GB
Too big Get file →
IQ3_XS17.3 GB 18.2 GB
Too big Get file →
Q3_K_S18.2 GB 19.2 GB
Too big Get file →
IQ3_S18.2 GB 19.2 GB
Too big Get file →
IQ3_M18.4 GB 19.4 GB
Too big Get file →
Q3_K_M20.1 GB 21.1 GB
Too big Get file →
Q3_K_L21.7 GB 22.7 GB
Too big Get file →
IQ4_XS22.4 GB 23.4 GB
Too big Get file →
Q4_023.8 GB 24.7 GB
Too big Get file →
Q4_K_S23.9 GB 24.8 GB
Too big Get file →
Q4_K_M25.4 GB 26.4 GB
Too big Get file →
Q4_126.3 GB 27.2 GB
Too big Get file →
Q5_K_S28.8 GB 29.8 GB
Too big Get file →
Q5_K_M29.7 GB 30.7 GB
Too big Get file →
Q6_K34.3 GB 35.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (8.68 GB). For 12 GB VRAM, IQ2_XS (12.39 GB) or IQ2_S (12.59 GB). For 16 GB VRAM, Q2_K (15.41 GB) or Q3_K_S (18.2 GB) provide a balance of size and performance. Memory estimates are approximate.

What GPU do you need for Qwen2.5 6x7B Six Pack Coder Instruct 38B?

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 IQ1_M (9.6 GB file, about 10.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K_S (14.4 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (22.4 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (29.7 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (34.3 GB file, about 35.3 GB in use).

Which Qwen2.5 6x7B Six Pack Coder Instruct 38B quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 6x7B Six Pack Coder Instruct 38B: it balances file size and quality well. Here it is a 25.4 GB file.

If memory is tight, the smallest file is IQ1_S at 8.7 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
Parameters42B (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)1,292
Last updated2025-07-17

Frequently asked questions about Qwen2.5 6x7B Six Pack Coder Instruct 38B

How much VRAM does Qwen2.5 6x7B Six Pack Coder Instruct 38B need?

About 26.4 GB at Q4_K_M with an 8K context window. That is the 25.4 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 6x7B Six Pack Coder Instruct 38B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen2.5 6x7B Six Pack Coder Instruct 38B GGUF?

It depends on the quant: IQ1_S is 8.7 GB, IQ1_M is 9.6 GB, IQ2_XXS is 11.1 GB, IQ2_XS is 12.4 GB, IQ2_S is 12.6 GB, IQ2_M is 13.8 GB and 17 more.

What context length does Qwen2.5 6x7B Six Pack Coder Instruct 38B 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 6x7B Six Pack Coder Instruct 38B GGUF?

The files are on Hugging Face in the mradermacher/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-38B-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 6x7B Six Pack Coder Instruct 38B 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 quant which is 8.68 GB and requires about 9.6 GB of VRAM at 8k context.

Does the model support vision tasks?

No, the model is focused on coding and does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →