Can Apple M2 Ultra run Ornith 1.5 35B-A3B?
Last updated:
Yes. Measured 132.5 tok/s generation (oMLX 0.7.1rc1 (MLX), MTP off, oQ4e-mtp mixed 4-bit MLX (20.5 GB loaded); source).
Every measured result for Ornith 1.5 35B-A3B on Apple M2 Ultra
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| Mac Studio M2 Ultra (60-core GPU, 64 GB): Qwen3.8 27B 4-bit at 33.6 tok/s, 41.6-64.3 with MTP; Ornith 1.5 35B-A3B at 132.5 tok/s (oMLX) | oQ4e-mtp mixed 4-bit MLX (20.5 GB loaded) | oMLX 0.7.1rc1 (MLX), MTP off | 132.5 | source |
Memory: Apple M2 Ultra has 64 GB. Ornith 1.5 35B-A3B weights are about 22.0 GB at Q4_K_M (35.95B 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 Ornith 1.5 35B-A3B: best home rig for Ornith 1.5 35B-A3B.
Ornith 1.5 35B-A3B on other hardware: Intel Arc Pro B70 · RTX 5090
Other models measured on Apple M2 Ultra: Qwen3.8 27B · gpt-oss 120B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run Ornith 1.5 35B-A3B 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.