QW

SWE-agent-LM-32B

QwenGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters32.8B
Context32K
Layers64
Architectureqwen2
Smallest quant9.0 GB
Quick answer

SWE-agent-LM-32B needs about 22.5 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 29 quants, from 9.0 GB (IQ1_S) to 65.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

SWE-agent-LM-32B – a 32.8B Qwen2 code‑focused LLM

SWE-agent-LM-32B is a 32.8B parameter model fine‑tuned from Qwen2.5‑Coder‑32B‑Instruct for software engineering tasks. It supports up to 131,072 tokens of context and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Code generation
  • Code reasoning
  • Tool usage

Limits

  • No vision support
  • Requires large VRAM for full precision
  • Long context may increase memory usage

Best for

  • Developing code assistants
  • Automating code fixes
  • Generating code snippets

Who it’s for. Engineers and researchers needing a large, open‑source code LLM. The model is suitable for local deployment on machines with sufficient GPU memory and for integration into software‑engineering workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S9.0 GB 11.6 GB
Too big Get file →
IQ1_M9.7 GB 12.4 GB
Too big Get file →
IQ2_XXS10.1 GB 12.8 GB
Too big Get file →
IQ2_S11.4 GB 14.0 GB
Too big Get file →
Q2_K_S11.5 GB 14.2 GB
Too big Get file →
IQ2_M12.0 GB 14.6 GB
Too big Get file →
Q2_K_M12.6 GB 15.2 GB
Too big Get file →
IQ3_XXS13.1 GB 15.8 GB
Too big Get file →
IQ3_XS13.8 GB 16.4 GB
Too big Get file →
IQ3_S14.5 GB 17.2 GB
Too big Get file →
IQ3_M14.7 GB 17.4 GB
Too big Get file →
Q3_K_S14.7 GB 17.4 GB
Too big Get file →
Q3_K_M16.1 GB 18.7 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.4 GB 21.1 GB
Too big Get file →
IQ4_NL18.7 GB 21.3 GB
Too big Get file →
Q4_K_S19.2 GB 21.8 GB
Too big Get file →
Q4_K_M19.8 GB 22.5 GB
Too big Get file →
Q4_120.5 GB 23.1 GB
Too big Get file →
Q5_022.5 GB 25.2 GB
Too big Get file →
Q5_K_S23.1 GB 25.7 GB
Too big Get file →
Q5_K_M23.4 GB 26.1 GB
Too big Get file →
Q5_124.6 GB 27.2 GB
Too big Get file →
Q6_K_M26.9 GB 29.5 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →
BF1636.3 GB 38.9 GB
Too big Get file →
F1636.3 GB 38.9 GB
Too big Get file →
BF1665.5 GB (2 parts) 68.2 GB
Too big Get file →
F1665.5 GB (2 parts) 68.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (8.99 GB file, ~11.6 GB memory). For 16 GB VRAM, Q4_K_M (19.82 GB file, ~22.5 GB memory) is a good balance. For 24 GB VRAM, Q5_K_M (23.41 GB file, ~26.1 GB memory) offers higher precision. Estimates are approximate.

What GPU do you need for SWE-agent-LM-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 IQ1_S (9.0 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.1 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.5 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_M (26.9 GB file, about 29.5 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (36.3 GB file, about 38.9 GB in use).

Which SWE-agent-LM-32B quant should you choose?

Q4_K_M is the usual starting point for SWE-agent-LM-32B: 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 IQ1_S 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

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

Source

Quantized byMungert
FamilyQwen
Licenseapache-2.0
Downloads (HF)864
Last updated2025-09-24

Frequently asked questions about SWE-agent-LM-32B

How much VRAM does SWE-agent-LM-32B need?

About 22.5 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 SWE-agent-LM-32B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SWE-agent-LM-32B GGUF?

It depends on the quant: IQ1_S is 9.0 GB, IQ1_M is 9.7 GB, IQ2_XXS is 10.1 GB, IQ2_S is 11.4 GB, Q2_K_S is 11.5 GB, IQ2_M is 12.0 GB and 23 more.

What context length does SWE-agent-LM-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-agent-LM-32B GGUF?

The files are on Hugging Face in the Mungert/SWE-agent-LM-32B-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-agent-LM-32B 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 SWE‑agent‑LM‑32B on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 11.6 GB of VRAM at 8 k context.

Does the model support image input?

No, SWE‑agent‑LM‑32B does not support vision tasks.

What is the maximum context length?

The model supports up to 131,072 tokens of context.

Other GGUFs of Qwen2.5-Coder-32B-Instruct

Similar models

Browse all →

More from Mungert

All by Mungert →

More Qwen models

All Qwen →

Other medium models

All medium models →