RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can DeepSeek V4 Flash Vision Exp run on the Mac M2 Ultra 192GB?

Yes. At 8K context the best fit is Q2_K, using about 111 GB of the 144 GB usable on the Mac M2 Ultra 192GB. Estimated speed ceiling: ~136 tokens/sec.

+ 0.5 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q2_K at 8K context then needs about 111 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Newer compressed-attention design: long-context figures are an upper bound.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •110 GB Fits111 GB Fits113 GB Fits122 GB Fits136
3-bit (Q3_K_M)140 GB Tight140 GB Tight142 GB Tight151 GB No107
4-bit (Q4_K_M)174 GB No175 GB No177 GB No186 GB No—
5-bit (Q5_K_M)203 GB No204 GB No206 GB No215 GB No—
6-bit (Q6_K)234 GB No234 GB No236 GB No245 GB No—
8-bit (Q8_0)302 GB No303 GB No305 GB No314 GB No—
16-bit (F16/BF16)568 GB No569 GB No571 GB No580 GB No—

• real GGUF file size from ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

DeepSeek V4 Flash Vision Exp on every GPU and Mac · Every model that runs on the Mac M2 Ultra 192GB · Apple Silicon guide · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (deepseek-ai/DeepSeek-V4-Flash-Vision-Exp), Apple specs. Model data last checked 2026-11-18; refreshed hourly.