DE

DeepSWE Preview

DeepsweGGUF by bartowskiUpdated 2025-07-03
Download on Hugging Face
Parameters32.8B
Context40K
Layers64
Architectureqwen3
Smallest quant9.0 GB
Quick answer

DeepSWE Preview needs about 22.4 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 9.0 GB (IQ2_XXS) to 65.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

32.8B Qwen3 coding agent trained with reinforcement learning

DeepSWE Preview is a 32.8B parameter Qwen3 model focused on software engineering tasks. It is trained with only reinforcement learning and achieves high performance on SWE-Bench-Verified. The model is fully open‑source under the MIT license.

Good at

  • Strong coding reasoning
  • Multi‑file editing
  • Tool‑based execution

Limits

  • Requires large VRAM for higher quants
  • No vision support
  • Context limited to 40960 tokens

Best for

  • Automated code repair
  • Complex codebase navigation
  • SWE agent prototyping

Who it’s for. Developers and researchers building or testing coding agents. The model is suitable for those who need a reinforcement‑learning‑only trained agent for software engineering tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.5 GB 13.2 GB
Too big Get file →
IQ2_M11.4 GB 14.0 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 →
Q2_K_L13.1 GB 15.8 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_M14.9 GB 17.6 GB
Too big Get file →
Q3_K_M16.0 GB 18.6 GB
Too big Get file →
Q3_K_L17.3 GB 20.0 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q3_K_XL18.0 GB 20.7 GB
Too big Get file →
IQ4_NL18.7 GB 21.3 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_M19.8 GB 22.4 GB
Too big Get file →
Q4_K_L20.3 GB 23.0 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_M23.2 GB 25.9 GB
Too big Get file →
Q5_K_L23.7 GB 26.3 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →
Q6_K_L27.3 GB 29.9 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →
BF1665.5 GB (2 parts) 68.2 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (9.02 GB file, ~11.7 GB memory). With 12 GB VRAM, IQ2_XS (9.95 GB, ~12.6 GB). For 16 GB VRAM, Q3_K_S (14.39 GB, ~17 GB). Higher quants provide better quality but need more memory.

What GPU do you need for DeepSWE Preview?

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 Q2_K_L (13.1 GB file, about 15.8 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_L (27.3 GB file, about 29.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).

Which DeepSWE Preview quant should you choose?

Q4_K_M is the usual starting point for DeepSWE Preview: it balances file size and quality well. Here it is a 19.8 GB file.

The Q8_0 file is 34.8 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 IQ2_XXS at 9.0 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

Architectureqwen3
Parameters32.8B
Layers64
Trained context40,960 tokens
KV cache (fp16)256 KB per token

Source

Quantized bybartowski
FamilyDeepswe
Licensemit
Downloads (HF)2,568
Last updated2025-07-03

Frequently asked questions about DeepSWE Preview

How much VRAM does DeepSWE Preview need?

About 22.4 GB at Q4_K_M with an 8K context window. That is the 19.8 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 DeepSWE Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSWE Preview GGUF?

It depends on the quant: IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.5 GB, IQ2_M is 11.4 GB, Q2_K is 12.3 GB, IQ3_XXS is 12.8 GB and 21 more.

What context length does DeepSWE Preview support?

The GGUF header lists a trained context length of 40,960 tokens (40K). 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 DeepSWE Preview GGUF?

The files are on Hugging Face in the bartowski/agentica-org_DeepSWE-Preview-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 DeepSWE Preview 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 DeepSWE Preview on 8 GB VRAM?

Yes, using the IQ2_XXS quant which requires about 11.7 GB of VRAM at 8K context.

Does the model support vision tasks?

No, DeepSWE Preview has no vision capabilities.

What is the maximum context length?

The model supports up to 40960 tokens.

Other GGUFs of DeepSWE-Preview

Similar models

Browse all →

More from bartowski

All by bartowski →

More Deepswe models

All Deepswe →

Other medium models

All medium models →