LL

Llm4Decompile 22b v2

LlmGGUF by mradermacherUpdated 2025-07-31
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant8.3 GB
Quick answer

Llm4Decompile 22b v2 needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 8.3 GB (Q2_K) to 23.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

LLM4Decompile 22b v2 – 22.2B‑parameter model for decompiling x86 assembly to C

LLM4Decompile 22b v2 is a 22.2‑billion‑parameter llama‑style model trained on 2 B tokens. It supports a maximum context of 32 768 tokens and is licensed under MIT. The model is designed to translate x86 assembly into C code.

Good at

  • Decompiling x86 assembly to C
  • Processing long code contexts up to 32 768 tokens
  • Integrating with Ghidra headless workflows

Limits

  • No vision or image input
  • Requires 8 k context for memory estimates
  • Large VRAM needed for higher‑quality quants

Best for

  • Automated binary reverse engineering
  • Generating C pseudo‑code from assembly
  • Enhancing Ghidra decompilation output

Who it’s for. Developers and reverse‑engineers who need accurate C code from binary analysis. The model is suitable for use with Ghidra headless scripts and other binary‑analysis pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.3 GB 10.7 GB
Too big Get file →
Q3_K_S9.6 GB 12.0 GB
Too big Get file →
Q3_K_M10.8 GB 13.1 GB
Too big Get file →
Q3_K_L11.7 GB 14.1 GB
Too big Get file →
IQ4_XS12.0 GB 14.4 GB
Too big Get file →
Q4_K_S12.7 GB 15.0 GB
Too big Get file →
Q4_K_M13.3 GB 15.7 GB
Too big Get file →
Q5_K_S15.3 GB 17.7 GB
Too big Get file →
Q5_K_M15.7 GB 18.1 GB
Too big Get file →
Q6_K18.3 GB 20.6 GB
Too big Get file →
Q8_023.6 GB 26.0 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (8.27 GB file, ~10.7 GB VRAM at 8 k context). For 12 GB VRAM, Q3_K_S (9.64 GB file, ~12 GB VRAM). For 16 GB VRAM, Q4_K_S (12.66 GB file, ~15 GB VRAM). Higher quants require proportionally more VRAM.

What GPU do you need for Llm4Decompile 22b v2?

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 Q3_K_S (9.6 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.3 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.6 GB file, about 26.0 GB in use).

Which Llm4Decompile 22b v2 quant should you choose?

Q4_K_M is the usual starting point for Llm4Decompile 22b v2: it balances file size and quality well. Here it is a 13.3 GB file.

The Q8_0 file is 23.6 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 8.3 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

Architecturellama
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilyLlm
Licensemit
Downloads (HF)677
Last updated2025-07-31

Frequently asked questions about Llm4Decompile 22b v2

How much VRAM does Llm4Decompile 22b v2 need?

About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 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 Llm4Decompile 22b v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llm4Decompile 22b v2 GGUF?

It depends on the quant: Q2_K is 8.3 GB, Q3_K_S is 9.6 GB, Q3_K_M is 10.8 GB, Q3_K_L is 11.7 GB, IQ4_XS is 12.0 GB, Q4_K_S is 12.7 GB and 5 more.

What context length does Llm4Decompile 22b v2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Llm4Decompile 22b v2 GGUF?

The files are on Hugging Face in the mradermacher/llm4decompile-22b-v2-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 Llm4Decompile 22b v2 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 LLM4Decompile 22b v2 on 8 GB VRAM?

Yes, the Q2_K quant uses 8.27 GB file size and requires about 10.7 GB VRAM at 8 k context, which is close to 8 GB but may need swapping.

Does the model support image or vision inputs?

No, the model only processes text and does not have vision capabilities.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of llm4decompile-22b-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llm models

All Llm →

Other medium models

All medium models →