397BTier 100Needs ~251.4 GB
Apple
Operating mode
Apple Silicon can fit a lot thanks to unified memory. This selector changes which serving posture we optimize for when surfacing the best local LLMs for this Mac.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Apple Silicon local AI performance. Excellent for local AI. Your Mac Studio M1 Ultra 64GB with 64 GB unified memory can run 125 models natively, 193 more with limits. The best match is Qwen 3.6 35B A3B at 56 tok/s for interactive local LLM use.
125
Run great
318
Total compatible
67B
Max parameters
56
Best tok/sEST.
Comparison guide
Top models ranked for coding, chat, and writing with FAQ and buyer guidance — the comparison-intent companion to this spec sheet.
Quick picks
Top recommendations for common local AI workloads on your Mac Studio M1 Ultra 64GB
Mac Studio M1 Ultra 64GB with 64 GB unified memory. Apple's first custom silicon for Mac, delivering excellent power efficiency and unified memory architecture for local AI inference.
All 374 models tested
Every model ranked by how well it runs on your Mac Studio M1 Ultra 64GB, grouped by fit quality
These models fit comfortably and run at full speed on your Mac.
These models run but may need quantization or have reduced context windows.
These models are too large for your Mac's unified memory.
Beyond LLMs
What AI tasks this Mac can handle — from text generation to image and video creation.
| Capability | Status | Representative Model |
|---|---|---|
| LLM Chat (7B) | Runs natively | Llama 3.1 8B Q4 |
| LLM Coding (30B) | Runs natively | Qwen 3 30B Q4 |
| LLM Large (70B) | Needs offload | Llama 3.1 70B Q4 |
| Image Gen (SDXL) | Runs natively | SDXL 1.0 FP16 |
| Image Gen (Flux) | Runs natively | Flux.1 Dev FP16 |
| Image Gen (SD 3.5) | Runs natively | SD 3.5 Large FP16 |
| Video Short (25f) | Runs natively | LTX Video 2B |
| Video Long (100f) | Won't fit | Wan Video 14B |
Same chip, more memory
Compare M1 configurations to see which models become available
16 GB unified memory
59
Run great
212
Total fit
32 GB unified memory
91
Run great
292
Total fit
Architecture
Apple M1 is the first Apple Silicon chip for Mac, featuring a unified memory architecture where CPU, GPU, and Neural Engine share the same high-bandwidth memory pool. Available in base, Pro, Max, and Ultra variants with 16-128 GB unified memory.
AI Relevance
Unified memory architecture is a game-changer for LLM inference — the entire memory pool is accessible to both CPU and GPU, eliminating the discrete VRAM bottleneck. An M1 Max with 64 GB can run 30B+ models that would be impossible on a 24 GB discrete GPU.
First-generation Apple Silicon with 8-core GPU. The unified memory architecture is particularly beneficial for LLM inference as it eliminates the PCIe bottleneck that discrete GPUs face when offloading.
All workloads
The best local LLM for each task on your Mac Studio M1 Ultra 64GB
Chat
SThis model is a direct match for chat. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Coding
SThis model is a direct match for coding. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Agentic Coding
SThis model is still usable for agentic-coding, but it is not the most specialized pick. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Reasoning
SThis model is a direct match for reasoning. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
RAG
SThis model is a direct match for rag. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Just out of reach
High-quality models that need a bit more memory
Image & Video Generation
50 of 52 models can generate images or video on your Mac Studio M1 Ultra 64GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | ~5.7s | S |
| Stable Diffusion 1.5Image | 512×768 | ~11.3s | S |
| Realistic Vision v5.1Image | 512×768 | ~11.3s | S |
| DreamShaper 8Image | 512×768 | ~11.3s | S |
| LCM DreamShaper v7Image | 512×768 | ~3.4s | S |
| PixArt-SigmaImage | 1024×1024 | ~45.3s | S |
| FramePack I2VVideo | 256×256 | ~2m 24s/frame | S |
| SDXL TurboImage | 512×512 | ~5.7s | S |
| SDXL LightningImage | 1024×1024 | ~17s | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | ~45.3s | S |
| Playground v2.5Image | 1024×1024 | ~1m 8s | S |
| RealVisXL v5.0Image | 1024×1024 | ~51s | S |
| DreamShaper XLImage | 1024×1024 | ~51s | S |
| Juggernaut XL v9Image | 1024×1024 | ~51s | S |
| Animagine XL 3.1Image | 1024×1024 | ~51s | S |
| Pony Diffusion V6 XLImage | 1024×1024 | ~51s | S |
| Animagine XL 4.0Image | 1024×1024 | ~51s | S |
| Illustrious XLImage | 1024×1024 | ~51s | S |
| Wan Video 2.1 1.3BVideo | 480×832 | ~33.1s/frame | S |
| Stable Diffusion 3.5 MediumImage | 1024×1024 | ~1m 19s | S |
| Flux.2 Klein 4BImage | 1024×1024 | ~13.6s | S |
| LTX Video 2BVideo | 1280×720 | ~39.4s/frame | S |
| KolorsImage | 1024×1024 | ~1m 31s | S |
| Stable CascadeImage | 1024×1024 | ~1m 53s | S |
| AuraFlow v0.3Image | 1536×1536 | ~3m 24s | S |
| Stable Diffusion 3.5 LargeImage | 1024×1024 | ~4m 9s | S |
| Stable Diffusion 3.5 Large TurboImage | 1024×1024 | ~45.3s | S |
| CogVideoX 2BVideo | 720×480 | ~39.4s/frame | S |
| HunyuanVideoVideo | 256×256 | ~2m 24s/frame | S |
| ChromaImage | 1024×1024 | ~45.3s | S |
| Z-Image TurboImage | 1536×1536 | ~46.8s | S |
| Flux.1 DevImage | 1024×1024 | ~3m 24s | S |
| Flux.1 SchnellImage | 1024×1024 | ~39.7s | S |
| LTX Video 13BVideo | 768×512 | ~1m 23s/frame | S |
| Flux.1 Kontext DevImage | 1024×1024 | ~3m 47s | S |
| AnimateDiff v1.5.3Video | 512×768 | ~20.7s/frame | S |
| Cosmos Diffusion 7BVideo | 1024×576 | ~1m 5s/frame | S |
| CogVideoX 5BVideo | 720×480 | ~56.8s/frame | S |
| Wan2.2 TI2V 5BVideo | 832×480 | ~56.8s/frame | S |
| Flux.2 Klein 9BImage | 1024×1024 | ~22.7s | S |
| Flux.1 Fill DevImage | 1024×1024 | ~3m 13s | S |
| Mochi 1 PreviewVideo | 848×480 | ~1m 15s/frame | A |
| HunyuanVideo 1.5Video | 544×960 | ~1m 10s/frame | A |
| Helios 14BVideo | 256×256 | ~2m 27s/frame | B |
| SkyReels V2 14BVideo | 256×256 | ~2m 27s/frame | B |
| Wan Video 2.1 14BVideo | 256×256 | ~2m 27s/frame | D |
| Wan Video 2.2 14BVideo | 256×256 | ~2m 27s/frame | D |
| Qwen ImageImage | 256×256 | ~2m 6s | D |
| Qwen Image EditImage | 256×256 | ~2m 6s | D |
| Flux.2 DevImage | 256×256 | ~35m 44s | D |
| MAGI-1Video | 256×256 | ~1m 46s/frame | F |
| HunyuanImage 3.0Image | 256×256 | ~2m 14s | F |
Image models estimated at 1024×1024 (28 steps, FP16). Video models estimated at 768×512 (25 frames, 30 steps, FP16). Actual performance varies with runtime and system load.
Get started in 2 minutes
Everything you need to start running models locally with Metal acceleration and Apple Silicon unified memory
Ollama runs natively on macOS with Metal GPU acceleration. One command to install.
curl -fsSL https://ollama.com/install.sh | shQwen 3.6 35B A3B is the best match for your Mac Studio M1 Ultra 64GB. Pull and run it:
ollama run qwen:3.6:35b:a3bUpgrade paths
See what you unlock with more unified memory
Upgrade options
RTX 6000 Ada 48GBNext step upUnlocks 2 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 27%.
~$6,800 MSRP
Unlocks 8 additional models that do not fit on the current setup.
~$2,499 MSRP
Unlocks 15 additional models that do not fit on the current setup.
~$2,499 MSRP
Unlocks 28 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 168%.
~$8,000 MSRP
Yes! Mac Studio M1 Ultra 64GB (64 GB unified memory) can run 125 models at full speed and 318 total. Top picks: Qwen 3.6 35B A3B (score: 98/100), Qwen3-Coder 30B A3B Instruct (score: 97/100), Qwen 3.5 35B A3B (score: 96/100). See the full tiered compatibility list above.
Mac Studio M1 Ultra 64GB has 64 GB of unified memory shared between CPU and GPU, all available for AI model inference. Unlike discrete GPUs with separate VRAM, unified memory means models can use the full 64 GB without data transfer overhead.
Not exactly. Unified memory is excellent for making larger models fit on Apple Silicon, because the CPU and GPU share one memory pool. But it is still not identical to dedicated VRAM on a high-bandwidth discrete GPU. For local AI, unified memory often wins on flexibility and capacity, while discrete GPUs can still win on raw tokens per second once a model fits comfortably.
Yes, Mac Studio M1 Ultra 64GB is excellent for running LLMs locally. With 64 GB unified memory and Metal acceleration, it handles 318 models with top scores above 80/100.
Because fit and speed are not the same thing. Mac Studio M1 Ultra 64GB can often fit larger models thanks to unified memory, but a smaller NVIDIA GPU with fast dedicated VRAM and mature CUDA kernels can still deliver higher decode throughput once the model fits. In practice, Apple Silicon is excellent for flexible local AI on one machine, while CUDA often stays ahead for the easiest setup and highest raw inference speed.
We recommend using llama.cpp on Mac Studio M1 Ultra 64GB. Install it with a single command, then pull your preferred model. llama.cpp supports Metal acceleration out of the box on Apple Silicon.
For coding on Mac Studio M1 Ultra 64GB, we recommend Qwen 3.6 27B. It achieves 21.9 tokens per second with 262K context window using 25.3 GB of unified memory. This model is a direct match for coding. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, lm-studio.
Yes, Mac Studio M1 Ultra 64GB with 64 GB unified memory can run Flux.1 Dev at FP16. Use ComfyUI or Draw Things for the best experience on macOS.
Mac Studio M1 Ultra 64GB (64 GB unified memory) supports various AI generation tasks. For image generation, SDXL and Stable Diffusion 3.5 run well with Metal acceleration. Flux.1 Dev also runs natively. For video, LTX Video 2.3 can generate short clips.
Mac Studio M1 Ultra 64GB is excellent for AI image generation. With 64 GB unified memory and Metal GPU acceleration, it runs all major diffusion models including Flux.1, SDXL, and SD 3.5.
There are 4 upgrade path(s) from Mac Studio M1 Ultra 64GB: RTX 6000 Ada 48GB (48 GB), MacBook Pro M4 Max 96GB (96 GB). Upgrading would unlock larger models like Qwen 3.5 397B A17B and Devstral 2 123B Instruct and faster inference.
Yes, Mac Studio M1 Ultra 64GB with 64 GB can run Qwen 3.5 27B at near-lossless Q8 quantization and the 35B-A3B MoE variant comfortably at Q4. For maximum quality, the 27B dense model at Q8 is the best choice. Both MLX and Ollama (llama.cpp) support Qwen 3.5 on Mac.
The best local LLMs for Mac Studio M1 Ultra 64GB (64 GB) are: Qwen 3.6 35B A3B (98/100, 56 tok/s), Qwen3-Coder 30B A3B Instruct (97/100, 67 tok/s), Qwen 3.5 35B A3B (96/100, 61 tok/s). These models fit natively in unified memory with room for context. For coding, try the top coding pick above. For general chat, the highest-scored model gives the best Apple Silicon local AI experience.
Mac Studio M1 Ultra 64GB achieves 39-56 tok/s for well-fitted models with 800 GB/s memory bandwidth. Token generation speed on Apple Silicon is primarily limited by memory bandwidth and fit. Comfortable reading speed is about 6-8 tokens per second, so most natively-fitting models will feel responsive for interactive chat. MLX generally delivers 10-20% better performance than llama.cpp on newer Apple Silicon chips.
Compare with similar
Related guides