Apple M2 Ultra (192GB)
The Apple M2 Ultra (192GB) has 192 GB VRAM and 800 GB/s memory bandwidth. It can run 64 of our 70 tracked models natively in VRAM at 8k context.
With 192 GB LPDDR5, the Apple M2 Ultra (192GB) is a workstation-tier GPU that can run 64 models natively. It handles 70B-class models at Q4 quantization.
The Apple M2 Ultra (192GB) is the base configuration of Apple's M2 Ultra chip, found in the Mac Pro and Mac Studio. Its 192GB of unified LPDDR5 memory at 800 GB/s can hold a 70B model in full Q4 quantization entirely in memory. While the M4 Ultra brings a 37% bandwidth improvement, the M2 Ultra remains fully supported by MLX and llama.cpp and is a capable long-term platform for local LLM inference at scale.
Apple M2 Ultra (192GB): Base M2 Ultra with 192GB at 800 GB/s.
70B at Q4 native ~11-15 t/s. Llama 405B at 1-bit (IQ1_M) ~2.3 t/s, 2-bit (Q2_K) for short sequences.
Same as 384GB. K-quants strongly preferred over IQ-quants.
| Vendor | Apple |
| Architecture | Apple M2 Ultra |
| CPU cores | 24 (16P + 8E) |
| VRAM | 192 GB (unified) |
| Memory type | LPDDR5 |
| Memory bandwidth | 800 GB/s |
| Compute backend | METAL |
| Tier | Workstation |
| Released | 2023 |
| Models (native) | 64 / 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 (64)
- MiniMax M1 456B456B · MMLU-Pro 81.1Q2_K · ~58.1 t/s
- Llama 3.1 405B Instruct405B · MMLU-Pro 73.3Q2_K · ~6 t/s
- Llama 4 Maverick 400B400B · MMLU-Pro 80.5Q2_K · ~157.3 t/s
- GLM-4.7 358B358B · MMLU-Pro 84.3Q3_K_M · ~64 t/s
- GLM-4.5 355B355B · MMLU-Pro 84.6Q3_K_M · ~64 t/s
- GLM-4.6 355B355B · MMLU-Pro 84.5Q3_K_M · ~64 t/s
- DeepSeek V4 Flash 284B284B · MMLU-Pro 86.3Q4_K_M · ~120.2 t/s
- Qwen3 235B-A22B (MoE)235B · MMLU-Pro 84.4Q5_K_M · ~62.1 t/s
- MiniMax M2.5 229B229B · MMLU-Pro 84.8Q5_K_M · ~136.6 t/s
- MiniMax M2.7 229B229B · MMLU-Pro 86.0Q5_K_M · ~136.6 t/s
- Mixtral 8x22B Instruct v0.1141B · MMLU-Pro 40.0Q8_0 · ~22.6 t/s
- Qwen 3.5 122B-A10B (MoE)122B · MMLU-Pro 86.7Q8_0 · ~88 t/s
- Nemotron 3 Super 120B120B · MMLU-Pro 83.7Q8_0 · ~73.3 t/s
- GPT-OSS 120B117B · MMLU-Pro 80.7Q8_0 · ~176 t/s
- Llama 4 Scout 109B109B · MMLU-Pro 74.3Q8_0 · ~51.8 t/s
- GLM-4.5 Air 106B106B · MMLU-Pro 81.4Q8_0 · ~73.3 t/s
- GLM-4.6V 106B106B · MMLU-Pro 79.9Q8_0 · ~73.3 t/s
- Qwen 2.5 72B Instruct72B · MMLU-Pro 71.1BF16 · ~5.6 t/s
- Llama 3.3 70B Instruct70B · MMLU-Pro 68.9BF16 · ~5.7 t/s
- DeepSeek R1 Distill Llama 70B70B · MMLU-Pro 70.0BF16 · ~5.7 t/s
- Llama 3.1 70B Instruct70B · MMLU-Pro 66.4BF16 · ~5.7 t/s
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7BF16 · ~34.1 t/s
- Command-R 35B35B · MMLU-Pro 33.0FP32 · ~5.7 t/s
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 84.2FP32 · ~73.3 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2FP32 · ~5.7 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0FP32 · ~5.8 t/s
- Qwen3 32B32.8B · MMLU-Pro 65.5FP32 · ~6.1 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0FP32 · ~6.2 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4FP32 · ~6.2 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0FP32 · ~6.2 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3FP32 · ~73.3 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2FP32 · ~6.5 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5FP32 · ~73.3 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0FP32 · ~7.4 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5FP32 · ~7.4 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2FP32 · ~7.4 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6FP32 · ~57.9 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8FP32 · ~8.3 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2FP32 · ~9 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9FP32 · ~55 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0FP32 · ~13.5 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7FP32 · ~13.6 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4FP32 · ~14.3 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6FP32 · ~16.4 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6FP32 · ~16.4 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0FP32 · ~21.7 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3FP32 · ~25 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0FP32 · ~25 t/s
- Qwen3 8B8B · MMLU-Pro 56.7FP32 · ~25 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3FP32 · ~26.3 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0FP32 · ~27.6 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6FP32 · ~50 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4FP32 · ~50 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4FP32 · ~52.6 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP32 · ~62.5 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~64.5 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~76.9 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~100 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~117.6 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~133.3 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~161.3 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~200 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~400 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~555.6 t/s
Too large for this GPU (6)
Compare Apple M2 Ultra (192GB) with other GPUs
- Apple M2 Ultra (192GB)vsApple M4 Ultra (192GB)192 GB each
- Apple M2 Ultra (192GB)vsApple M1 Ultra (128GB)+64 GB VRAM
- Apple M2 Ultra (192GB)vsNVIDIA RTX 4090+168 GB VRAM
- Apple M2 Ultra (192GB)vsNVIDIA RTX 6000 Ada+144 GB VRAM
- Apple M2 Ultra (192GB)vsAMD Instinct MI300X192 GB each
- Apple M2 Ultra (192GB)vsApple M3 Max (128GB)+64 GB VRAM
Frequently asked questions
- How much VRAM does the Apple M2 Ultra (192GB) have?
- The Apple M2 Ultra (192GB) has 192 GB of LPDDR5 with 800 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
- What is the Apple M2 Ultra (192GB) best for?
- With 192 GB of VRAM, the Apple M2 Ultra (192GB) 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 M2 Ultra (192GB) run locally?
- The Apple M2 Ultra (192GB) can run 64 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.3 70B Instruct at BF16, Llama 3.1 8B Instruct at FP32, Llama 3.2 3B Instruct at FP32.
- Can the Apple M2 Ultra (192GB) run Llama 3.3 70B Instruct?
- Yes. The Apple M2 Ultra (192GB) runs Llama 3.3 70B Instruct natively in VRAM at BF16 quantization, achieving approximately 5.7 tokens per second.
- Can the Apple M2 Ultra (192GB) run Qwen 3.6 27B?
- Yes. The Apple M2 Ultra (192GB) runs Qwen 3.6 27B natively in VRAM at FP32 quantization, achieving approximately 7.4 tokens per second.
- Can the Apple M2 Ultra (192GB) run Llama 3.1 8B Instruct?
- Yes. The Apple M2 Ultra (192GB) runs Llama 3.1 8B Instruct natively in VRAM at FP32 quantization, achieving approximately 25 tokens per second.