RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can granite 3.3 8b instruct run on the Mac M3 24GB?

Yes. At 8K context the best fit is Q8_0, using about 9.8 GB of the 16.1 GB usable on the Mac M3 24GB. Estimated speed ceiling: ~12 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •4.0 GB Fits4.6 GB Fits8.4 GB Fits23.4 GB No32
3-bit (Q3_K_M) •4.8 GB Fits5.5 GB Fits9.2 GB Fits24.2 GB No25
4-bit (Q4_K_M) •5.7 GB Fits6.3 GB Fits10.1 GB Fits25.1 GB No20
5-bit (Q5_K_M) •6.5 GB Fits7.1 GB Fits10.9 GB Fits25.9 GB No17
6-bit (Q6_K) •7.4 GB Fits8.0 GB Fits11.7 GB Fits26.7 GB No15
8-bit (Q8_0) •9.2 GB Fits9.8 GB Fits13.6 GB Fits28.6 GB No12
16-bit (F16/BF16) •16.3 GB No17.0 GB No20.7 GB No35.7 GB No—

• real GGUF file size from ibm-granite/granite-3.3-8b-instruct-GGUF. Speed is a bandwidth ceiling (100 GB/s), not a benchmark. Methodology.

More

granite 3.3 8b instruct on every GPU and Mac · Every model that runs on the Mac M3 24GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (ibm-granite/granite-3.3-8b-instruct), Apple specs. Data as of 2026-11-17.