LL

Llm4Decompile 22b v2

LlmGGUF by mradermacherUpdated 2025-02-27
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant4.8 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 23 quants, from 4.8 GB (IQ1_S) to 18.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

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

LLM4Decompile 22b v2 is a 22.2B‑parameter llama‑style model trained on 2B tokens. It supports a maximum context of 32768 tokens and is released under the MIT license. The model is optimized for translating assembly instructions into C code.

Good at

  • Decompiling x86 assembly to C
  • Handling long contexts up to 32768 tokens
  • Open‑source and MIT licensed

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Binary analysis pipelines
  • Automated decompilation tools
  • Code reverse engineering

Who it’s for. Developers and security researchers who need to convert assembly code into readable C. The model is suitable for integration into Ghidra or other reverse‑engineering workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.8 GB 7.2 GB
Tight Get file →
IQ1_M5.3 GB 7.6 GB
Tight Get file →
IQ2_XXS6.0 GB 8.4 GB
Too big Get file →
IQ2_XS6.6 GB 9.0 GB
Too big Get file →
IQ2_S7.0 GB 9.4 GB
Too big Get file →
IQ2_M7.6 GB 10.0 GB
Too big Get file →
Q2_K_S7.7 GB 10.0 GB
Too big Get file →
Q2_K8.3 GB 10.7 GB
Too big Get file →
IQ3_XXS8.6 GB 11.0 GB
Too big Get file →
IQ3_XS9.2 GB 11.6 GB
Too big Get file →
Q3_K_S9.6 GB 12.0 GB
Too big Get file →
IQ3_S9.7 GB 12.1 GB
Too big Get file →
IQ3_M10.1 GB 12.4 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_XS11.9 GB 14.3 GB
Too big Get file →
Q4_012.6 GB 15.0 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 →
Q4_113.9 GB 16.3 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 →

For an 8 GB VRAM budget, IQ1_S (file size 4.83 GB, estimated 7.2 GB memory at 8k context) is a good choice. If more VRAM is available, IQ1_M (5.27 GB, 7.6 GB memory) or IQ2_XXS (6 GB, 8.4 GB memory) can be used for higher quality. Larger quants such as Q4_K_M or Q5_K_M require more than 15 GB 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: the best quant that fits is IQ1_M (5.3 GB file, about 7.6 GB in use).
  • 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).

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.

If memory is tight, the smallest file is IQ1_S at 4.8 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)565
Last updated2025-02-27

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?

Yes, with IQ1_M: the 5.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: IQ1_S is 4.8 GB, IQ1_M is 5.3 GB, IQ2_XXS is 6.0 GB, IQ2_XS is 6.6 GB, IQ2_S is 7.0 GB, IQ2_M is 7.6 GB and 17 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-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 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 IQ1_S quant uses about 7.2 GB memory at 8k context, fitting within an 8 GB VRAM limit.

Does the model support vision tasks?

No, the model is text‑only and does not include 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 →