Can the Apple M2 Ultra (192GB) run Mixtral 8x7B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
Yes. The Apple M2 Ultra (192GB) can run Mixtral 8x7B fully in unified memory at FP16 (full quality), using about 95.1 GB of the 144 GB available, at roughly 19 tokens/second.
Run it with Ollama
With Ollama installed, one command downloads and starts Mixtral 8x7B:
ollama run mixtral:8x7bOllama's default download is Q4_K_M (about 30 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.
Run it in the cloud
No Apple M2 Ultra (192GB)? Run Mixtral 8x7B in the cloud.
Rent a cloud GPU by the hour. No upfront cost, stop any time.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 144 GB the Apple M2 Ultra (192GB) can use. macOS lets the GPU use about 144 GB of the 192 GB unified memory by default.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 95.1 GB | Fits | ~19 tok/s | |
| Q8_0 | Near-lossless | 51.3 GB | Fits | ~35 tok/s | |
| Q6_K | Excellent | 40 GB | Fits | ~45 tok/s | |
| Q5_K_M | Very good | 34.9 GB | Fits | ~52 tok/s | |
| Q4_K_M | Good, most popular | 30 GB | Fits | ~61 tok/s | |
| Q3_K_M | Noticeably degraded | 24.5 GB | Fits | ~76 tok/s | |
| Q2_K | Heavily degraded | 19.2 GB | Fits | ~99 tok/s |
GPUs that run Mixtral 8x7B comfortably
Models that run well on the Apple M2 Ultra (192GB)
Frequently asked questions
Can Apple M2 Ultra (192GB) run Mixtral 8x7B?
Yes. The Apple M2 Ultra (192GB) can run Mixtral 8x7B fully in unified memory at FP16 (full quality), using about 95.1 GB of the 144 GB available, at roughly 19 tokens/second.
How much VRAM does Mixtral 8x7B need?
About 30 GB at Q4_K_M with 8,192 tokens of context, and about 95.1 GB at full FP16 precision.
How fast is Mixtral 8x7B on the Apple M2 Ultra (192GB)?
Roughly 19 tokens per second at FP16, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.