CanItRun Logocanitrun.

Apple M1 Ultra (128GB)

The Apple M1 Ultra (128GB) has 128 GB VRAM and 800 GB/s memory bandwidth. It can run 58 of our 70 tracked models natively in VRAM at 8k context.

With 128 GB LPDDR5, the Apple M1 Ultra (128GB) is a workstation-tier GPU that can run 58 models natively. It handles 70B-class models at Q4 quantization.

Apple M1 Ultra (128GB): 2022 first-gen Ultra with 128GB LPDDR5 at 800 GB/s. 20-core CPU, 64-core GPU.

70B at Q4 ~6-10 t/s decode. ~50-60% of M2 Ultra performance.

Full MLX support. llama.cpp Metal functional but less optimized than M2/M3. Lacks some optimizations for irregular bit-widths.

VendorApple
ArchitectureApple M1 Ultra
CPU cores20 (16P + 4E)
VRAM128 GB (unified)
Memory typeLPDDR5
Memory bandwidth800 GB/s
Compute backendMETAL
TierWorkstation
Released2022
Models (native)58 / 70
Models (offload)0 / 70
Software: MLX gives the best performance on Apple Silicon; llama.cpp Metal backend is a solid alternative. Both are well-supported by Ollama.

Popular models for this GPU

Models this GPU runs natively in VRAM (58)

Too large for this GPU (12)

Compare Apple M1 Ultra (128GB) with other GPUs

Frequently asked questions

How much VRAM does the Apple M1 Ultra (128GB) have?
The Apple M1 Ultra (128GB) has 128 GB of LPDDR5 with 800 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
What is the Apple M1 Ultra (128GB) best for?
With 128 GB of VRAM, the Apple M1 Ultra (128GB) is a server-class GPU designed for running the largest open-weight models (70B–405B) at high quantization with ample context.
What LLMs can the Apple M1 Ultra (128GB) run locally?
The Apple M1 Ultra (128GB) can run 58 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at Q8_0, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.
Can the Apple M1 Ultra (128GB) run Llama 3.3 70B Instruct?
Yes. The Apple M1 Ultra (128GB) runs Llama 3.3 70B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 11.4 tokens per second.
Can the Apple M1 Ultra (128GB) run Qwen 3.6 27B?
Yes. The Apple M1 Ultra (128GB) runs Qwen 3.6 27B natively in VRAM at FP32 quantization, achieving approximately 7.4 tokens per second.
Can the Apple M1 Ultra (128GB) run Llama 3.1 8B Instruct?
Yes. The Apple M1 Ultra (128GB) runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 25 tokens per second.