DE

Sk2Decompile Ident 6.7

DecompileGGUF by mradermacherUpdated 2026-01-25
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

Sk2Decompile Ident 6.7 needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.5 GB (Q2_K) to 13.5 GB (F16).

Sk2Decompile Ident 6.7 – LLM-based identifier naming for binary decompilation

Sk2Decompile Ident 6.7 is a 6.74 billion‑parameter llama model trained on C language Linux‑x64 code. It generates human‑readable identifiers from IDA pseudocode. The model is released under the MIT license.

Good at

  • Identifier naming in decompiled C code
  • Two‑phase decompilation workflow
  • LLM‑based post‑processing

Limits

  • No vision support
  • Requires pre‑processed IDA output
  • Large VRAM needed for higher‑quality quants

Best for

  • Binary decompilation projects
  • Reverse engineering pipelines
  • Automated code cleanup

Who it’s for. Engineers and researchers working on binary reverse engineering who need accurate identifier generation. The model is suitable for those who can prepare IDA decompilation outputs and run inference locally.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 7.3 GB
Tight Get file →
Q3_K_S3.0 GB 7.7 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →
F1613.5 GB 18.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (2.53 GB, ~7.3 GB RAM) or Q3_K_S (2.95 GB, ~7.7 GB RAM). If 12 GB VRAM is available, Q8_0 (7.16 GB, ~12 GB RAM) offers full precision. Higher‑quality quants such as Q5_K_M require ~9.6 GB RAM and 5.53 GB file size.

What GPU do you need for Sk2Decompile Ident 6.7?

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 Q3_K_S (3.0 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which Sk2Decompile Ident 6.7 quant should you choose?

Q4_K_M is the usual starting point for Sk2Decompile Ident 6.7: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.5 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
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyDecompile
Licensemit
Downloads (HF)196
Last updated2026-01-25

Frequently asked questions about Sk2Decompile Ident 6.7

How much VRAM does Sk2Decompile Ident 6.7 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Sk2Decompile Ident 6.7 on an 8 GB GPU?

Yes, with Q3_K_S: the 3.0 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sk2Decompile Ident 6.7 GGUF?

It depends on the quant: Q2_K is 2.5 GB, Q3_K_S is 3.0 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, IQ4_XS is 3.6 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does Sk2Decompile Ident 6.7 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download Sk2Decompile Ident 6.7 GGUF?

The files are on Hugging Face in the mradermacher/sk2decompile-ident-6.7-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 Sk2Decompile Ident 6.7 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 Sk2Decompile Ident 6.7 on 8 GB VRAM?

Yes, the Q2_K quant uses 2.53 GB file size and requires about 7.3 GB RAM at 8k context, fitting within 8 GB VRAM.

Does the model support other programming languages?

Training was done on C language Linux‑x64 code; performance may degrade for other languages or architectures.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of sk2decompile-ident-6.7b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Decompile models

All Decompile →

Other small models

All small models →