Can MacBook Pro M1 Max 64GB run Llama-4-Scout-17B-16E-Instruct?

Apple · 64 GB LPDDR5 · 400 GB/s bandwidth · Meta · 109.0B (active 17.0B) · MoE · model ctx up to 10240K

METAL

Partly — Llama-4-Scout-17B-16E-Instruct at Q4 fits the MacBook Pro M1 Max 64GB (64 GB LPDDR5) at 4K context (≈ 62.65 GB) but not at the default 8K (≈ 64.35 GB needed). Use a shorter context or partial offload. Decode at Q4/8K: ≈ 42.3 tok/s (estimated, batch 1). FP16 needs ≈ 222.4 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	62.65 GB	Yes	15.0 ± est.
Q4	8K default	64.35 GB	No	42.3 ± est.
Q4	32K	74.55 GB	No	31.5 ± est.
FP16	4K	220.7 GB	No	1.0 ± est.
FP16	8K default	222.4 GB	No	1.0 ± est.
FP16	32K	232.6 GB	No	0.9 ± 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	MacBook Pro M1 Max 64GB VRAM
Q4	59.95 GB	3.4 GB	1 GB	64.35 GB	64 GB
FP16	218.0 GB	3.4 GB	1 GB	222.4 GB	64 GB

Other GPUs that run Llama-4-Scout-17B-16E-Instruct

• B200 192GB SXM — ≈299.5 tok/s Q4 est.
• MI300X 192GB — ≈198.4 tok/s Q4 est.
• H200 141GB SXM5 — ≈179.7 tok/s Q4 est.
• H100 80GB SXM5 — ≈125.4 tok/s Q4 est.
• Gaudi 3 128GB — ≈122.6 tok/s Q4 est.
• A100 80GB SXM4 — ≈76.3 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — ≈30.7 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈29.9 tok/s Q4 est.

All GPUs for Llama-4-Scout-17B-16E-Instruct →

Other models for the MacBook Pro M1 Max 64GB

• MiniCPM5-1B — ≈235.7 tok/s Q4 est.
• Qwen3.5-2B — ≈127.3 tok/s Q4 est.
• DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx — ≈110.7 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈84.8 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈84.8 tok/s Q4 est.
• GLM-4.7-Flash — ≈84.8 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈84.8 tok/s Q4 est.
• Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 — ≈84.8 tok/s Q4 est.

All models on the MacBook Pro M1 Max 64GB →