← AI Hashrate 中文

Can MacBook Neo A18 Pro 8GB run Hy3?

Apple · 8 GB LPDDR5X · 60 GB/s bandwidth · Tencent · 295.0B (active 21.0B) · MoE · model ctx up to 256K

❌ No — Hy3 Q4 needs 167.45 GB, card only has 8 GB
VRAM: 167.45 GB needed of 8 GB
FF · No FitComposite score: VRAM headroom × 0.5 + tok/s speed × 0.5. Q4 @ 8K context.
METAL
Your GPU won't fit Hy3, but runs these similar models: Qwen2.5-7B-Instruct, gemma-4-E2B-itor☁️ Rent on RunPod from ~$0.50/hr
Estimates from memory-bandwidth formula; rows marked "measured" override. Methodology.

Fit & speed by quant and context

QuantContextVRAM neededFits?tok/s (decode)
Q44K167.45 GBNo
Q48K default168.7 GBNo
Q432K176.2 GBNo
FP164K592.25 GBNo
FP168K default593.5 GBNo
FP1632K601.0 GBNo

Fits = weights + KV(ctx) + 0.5 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

QuantWeightsKV cacheOverheadTotal neededMacBook Neo A18 Pro 8GB VRAM
Q4165.2 GB2.5 GB0.5 GB168.7 GB8 GB
FP16590.0 GB2.5 GB0.5 GB593.5 GB8 GB

Other GPUs that run Hy3

All GPUs for Hy3 →

Other models for the MacBook Neo A18 Pro 8GB

All models on the MacBook Neo A18 Pro 8GB →