MA

Magicoder DS 6.7B

MagicoderGGUF by mradermacherUpdated 2026-10-24
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

Magicoder DS 6.7B needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 13 quants, from 2.5 GB (Q2_K) to 13.5 GB (F16).

Magicoder DS 6.7B – a coding‑focused LLM

Magicoder DS 6.7B is a 6.74 billion‑parameter llama architecture model fine‑tuned for code generation. It supports a 16384‑token context window and is available in multiple GGUF quantizations. The model is released under a DeepSeek license.

Good at

  • Code generation
  • Programming assistance
  • Debugging help

Limits

  • No vision support
  • Not suited for non‑coding tasks
  • License is DeepSeek

Best for

  • Writing scripts
  • Explaining code snippets
  • Automating coding workflows

Who it’s for. Developers and researchers needing a lightweight code model. It is ideal for local inference with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 7.3 GB
Tight Get file →
Q3_K_S3.0 GB 7.7 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
F1613.5 GB 18.3 GB
Too big Get file →

For 8 GB VRAM, Q4_K_M (4.08 GB file, 8.9 GB memory) is a good balance. If memory is tighter, Q3_K_S (2.95 GB file, 7.7 GB memory) fits. For higher quality and more memory, Q5_K_M (4.79 GB file, 9.6 GB memory) is recommended.

What GPU do you need for Magicoder DS 6.7B?

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 Q3_K_S (3.0 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which Magicoder DS 6.7B quant should you choose?

Q4_K_M is the usual starting point for Magicoder DS 6.7B: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.5 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

Architecturellama
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyMagicoder
Licenseother
Downloads (HF)743
Last updated2026-10-24

Frequently asked questions about Magicoder DS 6.7B

How much VRAM does Magicoder DS 6.7B need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Magicoder DS 6.7B on an 8 GB GPU?

Yes, with Q3_K_S: the 3.0 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 Magicoder DS 6.7B GGUF?

It depends on the quant: Q2_K is 2.5 GB, Q3_K_S is 3.0 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, IQ4_XS is 3.6 GB, Q4_0 is 3.8 GB and 7 more.

What context length does Magicoder DS 6.7B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download Magicoder DS 6.7B GGUF?

The files are on Hugging Face in the mradermacher/Magicoder-DS-6.7B-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 Magicoder DS 6.7B use?

Hugging Face lists the license as other. 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 Magicoder DS 6.7B on 8 GB VRAM?

Yes, using the Q4_K_M quantization requires about 8.9 GB memory at 8k context, which fits within 8 GB VRAM with some overhead.

Does this model support image input?

No, Magicoder DS 6.7B is a text‑only model with no vision capabilities.

What license does the model use?

The model is released under a DeepSeek license.

Other GGUFs of Magicoder-DS-6.7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Magicoder models

All Magicoder →

Other small models

All small models →