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

Can SingVL S1 4B run on the Mac M4 32GB?

Yes. At 8K context the best fit is F16, using about 9.0 GB of the 21.4 GB usable on the Mac M4 32GB. Estimated speed ceiling: ~14 tokens/sec.

+ 0.6 GB with image input. The figures on this page are for text only. Sending images also loads the vision projector (mmproj) file: F16 at 8K context then needs about 9.6 GB (still fits). Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.8 GB Fits2.9 GB Fits3.7 GB Fits6.7 GB Fits63
3-bit (Q3_K_M) •3.1 GB Fits3.2 GB Fits4.0 GB Fits7.0 GB Fits53
4-bit (Q4_K_M) •3.5 GB Fits3.6 GB Fits4.4 GB Fits7.4 GB Fits44
5-bit (Q5_K_M) •3.9 GB Fits4.0 GB Fits4.7 GB Fits7.7 GB Fits39
6-bit (Q6_K) •4.2 GB Fits4.3 GB Fits5.1 GB Fits8.1 GB Fits35
8-bit (Q8_0) •5.2 GB Fits5.3 GB Fits6.0 GB Fits9.0 GB Fits27
16-bit (F16/BF16) •8.8 GB Fits9.0 GB Fits9.7 GB Fits12.7 GB Fits14

• real GGUF file size from maternion/SingVL-S1-4B-GGUF. Speed is a bandwidth ceiling (120 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

SingVL S1 4B on every GPU and Mac · Every model that runs on the Mac M4 32GB · 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 (inclusionAI/SingVL_S1_4B), Apple specs. Model data last checked 2026-11-17; refreshed hourly.