← AI Hashrate 中文

Can MacBook Neo A18 Pro 8GB run Ornith-1.0-9B?

Apple · 8 GB LPDDR5X · 60 GB/s bandwidth · DeepReinforce · 9.0B · model ctx up to 256K

❌ No — Ornith-1.0-9B Q4 needs 6.17 GB, card only has 8 GB
VRAM: 6.17 GB needed of 8 GB
Speed: ~11.0 tok/s (estimated)
FF · No FitComposite score: VRAM headroom × 0.5 + tok/s speed × 0.5. Q4 @ 8K context.
METAL
Your GPU won't fit Ornith-1.0-9B, 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)
Q44K6.17 GBNo11.5 ± est.
Q48K default6.29 GBNo11.0 ± est.
Q432K7.04 GBNo8.7 ± est.
FP164K19.12 GBNo0.3 ± est.
FP168K default19.25 GBNo0.3 ± est.
FP1632K20.0 GBNo0.3 ± est.

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
Q45.04 GB0.25 GB0.5 GB6.29 GB8 GB
FP1618.0 GB0.25 GB0.5 GB19.25 GB8 GB

Other GPUs that run Ornith-1.0-9B

All GPUs for Ornith-1.0-9B →

Other models for the MacBook Neo A18 Pro 8GB

All models on the MacBook Neo A18 Pro 8GB →