Rent a GPU

Can the Apple M2 Ultra (192GB) run Mistral 7B v0.3?

Apple M2 Ultra (192GB) × Mistral 7B v0.38K context
YesRuns fully on the GPU
Memory at FP1616.2 GB of 144 GB
Weights 14.5 GBKV cache 1.1 GBRuntime 0.6 GB
QuantFP16Full quality
Memory16.2 GBof 144 GB usable
Speed~33tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The Apple M2 Ultra (192GB) can run Mistral 7B v0.3 fully in unified memory at FP16 (full quality), using about 16.2 GB of the 144 GB available, at roughly 33 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Mistral 7B v0.3:

ollama run mistral:7b

Ollama's default download is Q4_K_M (about 6.1 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M2 Ultra (192GB)

Run it in the cloud

No Apple M2 Ultra (192GB)? Run Mistral 7B v0.3 in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

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.

QuantQualityMemoryFits?Speed
FP16Full quality16.2 GBFits~33 tok/s
Q8_0Near-lossless9.4 GBFits~62 tok/s
Q6_KExcellent7.6 GBFits~81 tok/s
Q5_K_MVery good6.8 GBFits~93 tok/s
Q4_K_MGood, most popular6.1 GBFits~109 tok/s
Q3_K_MNoticeably degraded5.2 GBFits~135 tok/s
Q2_KHeavily degraded4.4 GBFits~177 tok/s

GPUs that run Mistral 7B v0.3 comfortably

Models that run well on the Apple M2 Ultra (192GB)

Frequently asked questions

Can Apple M2 Ultra (192GB) run Mistral 7B v0.3?

Yes. The Apple M2 Ultra (192GB) can run Mistral 7B v0.3 fully in unified memory at FP16 (full quality), using about 16.2 GB of the 144 GB available, at roughly 33 tokens/second.

How much VRAM does Mistral 7B v0.3 need?

About 6.1 GB at Q4_K_M with 8,192 tokens of context, and about 16.2 GB at full FP16 precision.

How fast is Mistral 7B v0.3 on the Apple M2 Ultra (192GB)?

Roughly 33 tokens per second at FP16, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.