LLM4Decompile 6.7B V2 on Apple M2 Ultra (64 GB)

Can the Apple M2 Ultra (64 GB) run LLM4Decompile 6.7B V2?

Yes, it runs great

Runs great. At Q8_0 it needs about 15.9 GB of 48.0 GB usable, with an estimated speed of 63.9 tok/s.

Best quant: Q8_0
Generation speed: 63.9 tok/s
Prompt processing: 2,502 tok/s
First token (1K prompt): 0.4 s
Largest safe context: 8K

Best app to run it on the Apple M2 Ultra (64 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open LLM4Decompile 6.7B V2 in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download LLM4Decompile 6.7B V2

Recommended for the Apple M2 Ultra (64 GB): Q8_0. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q8_0 file (opens in a new tab)

huggingface.co/DevQuasar-7/LLM4Binary.llm4decompile-6.7b-v2-GGUF (opens in a new tab)

ollama run hf.co/DevQuasar-7/LLM4Binary.llm4decompile-6.7b-v2-GGUF:Q8_0

Original weights · Hugging Face

Full-precision files from LLM4Binary, for fine-tuning, vLLM, Transformers.

huggingface.co/LLM4Binary/llm4decompile-6.7b-v2 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from LLM4Binary. The weights themselves download from Hugging Face.

github.com/albertan017/LLM4Decompile (opens in a new tab)

Official code and the Ghidra script that feeds decompiler output to the V2 models.

git clone https://github.com/albertan017/LLM4Decompile

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the Apple M2 Ultra (64 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	14.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	7.6 / 15
Match score	62.0 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Apple M2 Ultra (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	11.4 GB	48.0 GB	206 tok/s	Runs great	22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	12.0 GB	48.0 GB	162 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	12.8 GB	48.0 GB	125 tok/s	Runs great	30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	13.5 GB	48.0 GB	104 tok/s	Runs great	31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	14.3 GB	48.0 GB	87.1 tok/s	Runs great	31Basic quality (D) · 31 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	15.9 GB	48.0 GB	63.9 tok/s	Runs great	32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	22.2 GB	48.0 GB	29.4 tok/s	Runs well	32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 51.1 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 62.3 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 68.2 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 F16 · 43.1 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5060 Ti 16GB Q8_0 · 41.5 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 83.1 tok/s · Runs great

Quick answers

How much memory does LLM4Decompile 6.7B V2 need on the M2 Ultra 64GB?

At Q8_0 it needs about 15.9 GB. The M2 Ultra 64GB has 48.0 GB usable.

How fast is LLM4Decompile 6.7B V2 on the M2 Ultra 64GB?

About 63.9 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of LLM4Decompile 6.7B V2 should I use on the M2 Ultra 64GB?

Q8_0. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.