Can Mac Studio M3 Ultra 96GB run Qwen3-Coder-Next?

Apple · 96 GB LPDDR5 · 819 GB/s bandwidth · Alibaba · 79.7B (active 3B) · MoE · model ctx up to 256K

Yes — the Mac Studio M3 Ultra 96GB (96 GB LPDDR5) can run Qwen3-Coder-Next. At Q4 with the default 8K context it needs ≈ 45.44 GB VRAM (weights 43.84 GB + KV cache 0.6 GB + 1 GB runtime overhead), which fits within 96 GB. Decode at Q4/8K: ≈ 173.7 tok/s (estimated, batch 1). FP16 needs ≈ 161.0 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	45.14 GB	Yes	173.7 est.
Q4	8K default	45.44 GB	Yes	173.7 est.
Q4	32K	47.24 GB	Yes	173.7 est.
FP16	4K	160.7 GB	No	48.7 est.
FP16	8K default	161.0 GB	No	48.5 est.
FP16	32K	162.8 GB	No	47.5 est.

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	Mac Studio M3 Ultra 96GB VRAM
Q4	43.84 GB	0.6 GB	1 GB	45.44 GB	96 GB
FP16	159.4 GB	0.6 GB	1 GB	161.0 GB	96 GB

Other GPUs that run Qwen3-Coder-Next

• B200 192GB SXM — ≈1697.0 tok/s Q4 est.
• MI300X 192GB — ≈1124.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈1018.2 tok/s Q4 est.
• H100 80GB SXM5 — ≈710.6 tok/s Q4 est.
• Gaudi 3 128GB — ≈694.9 tok/s Q4 est.
• A100 80GB SXM4 — ≈432.5 tok/s Q4 est.
• RTX 6000 Ada 48GB — ≈203.6 tok/s Q4 est.
• L40S 48GB — ≈183.3 tok/s Q4 est.

All GPUs for Qwen3-Coder-Next →

Other models for the Mac Studio M3 Ultra 96GB

• Qwen3-0.6B — ≈651.5 tok/s Q4 est.
• gemma-3-1b-it — ≈521.2 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈434.3 tok/s Q4 est.
• Qwen3-1.7B — ≈260.6 tok/s Q4 est.
• Qwen3-30B-A3B — ≈173.7 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈173.7 tok/s Q4 est.
• GLM-4.7-Flash — ≈173.7 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈173.7 tok/s Q4 est.

All models on the Mac Studio M3 Ultra 96GB →