Can Apple M4 Pro run Flint 40B-A2.5B?
Yes. Measured 127.9 tok/s generation (Kapitsa (PR #286), int4 MLX (RecursiveSI/flint-int4); source).
Every measured result for Flint 40B-A2.5B on Apple M4 Pro
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| MacBook Pro M4 Pro 48 GB: Flint 40B-A2.5B 4-bit at 127.9 tok/s (Kapitsa), 126.6 (rec), 79.6 (llama.cpp) | int4 MLX (RecursiveSI/flint-int4) | Kapitsa (PR #286) | 127.9 | source |
| MacBook Pro M4 Pro 48 GB: Flint 40B-A2.5B 4-bit at 127.9 tok/s (Kapitsa), 126.6 (rec), 79.6 (llama.cpp) | int4 MLX (same files) | rec 0.1.0 (Recursive) | 126.56 | source |
| MacBook Pro M4 Pro 48 GB: Flint 40B-A2.5B 4-bit at 127.9 tok/s (Kapitsa), 126.6 (rec), 79.6 (llama.cpp) | Q4_1 GGUF (RecursiveSI/flint-int4-gguf) | llama.cpp b11804, all layers on GPU, -fa on | 79.57 | source |
Memory: Apple M4 Pro has 48 GB. Flint 40B-A2.5B weights are about 24.3 GB at Q4_K_M (39.8B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for Flint 40B-A2.5B: best home rig for Flint 40B-A2.5B.
Flint 40B-A2.5B on other hardware: RTX 3090 · RTX 4090
Not enough VRAM? Rent before you buy. Run Flint 40B-A2.5B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.