SW

SWE Dev 32B

SweGGUF by mradermacherUpdated 2025-07-29
Download on Hugging Face
Parameters32.8B
Context32K
Layers64
Architectureqwen2
Smallest quant7.3 GB
Quick answer

SWE Dev 32B needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 7.3 GB (IQ1_S) to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

SWE Dev 32B – 32.8B Qwen2 model for software engineering tasks

SWE Dev 32B is a 32.8B parameter Qwen2 model trained for software engineering tasks. It supports tool use and a 32768 token context window. The model is released under the MIT license.

Good at

  • Software engineering code generation
  • Issue tracking assistance
  • Test case generation

Limits

  • No vision support
  • Requires large VRAM for full context
  • MIT license allows free use

Best for

  • Developer agent workflows
  • Code review automation
  • SWE-bench evaluation

Who it’s for. Ideal for researchers and developers building software engineering agents. Supports tool use and large context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.3 GB 9.9 GB
Too big Get file →
IQ1_M7.9 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.4 GB 13.0 GB
Too big Get file →
IQ2_M11.3 GB 13.9 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.8 GB 17.5 GB
Too big Get file →
Q3_K_M15.9 GB 18.6 GB
Too big Get file →
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.3 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.27 GB file, 9.9 GB memory at 8k context). For 16 GB VRAM, use Q4_K_M (19.85 GB file, 22.5 GB memory). For 32 GB VRAM, use Q6_K (26.89 GB file, 29.5 GB memory).

What GPU do you need for SWE Dev 32B?

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 IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which SWE Dev 32B quant should you choose?

Q4_K_M is the usual starting point for SWE Dev 32B: it balances file size and quality well. Here it is a 19.9 GB file.

If memory is tight, the smallest file is IQ1_S at 7.3 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

Architectureqwen2
Parameters32.8B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilySwe
Licensemit
Downloads (HF)766
Last updated2025-07-29

Frequently asked questions about SWE Dev 32B

How much VRAM does SWE Dev 32B need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 SWE Dev 32B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SWE Dev 32B GGUF?

It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB and 17 more.

What context length does SWE Dev 32B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download SWE Dev 32B GGUF?

The files are on Hugging Face in the mradermacher/SWE-Dev-32B-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 SWE Dev 32B use?

Hugging Face lists the license as mit. 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 SWE Dev 32B on 8 GB VRAM?

The smallest quant IQ1_S requires 9.9 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision?

No, it only has text and tool abilities.

What license does it use?

MIT license, allowing free use and modification.

Other GGUFs of SWE-Dev-32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Swe models

All Swe →

Other medium models

All medium models →