Apple · 96 GB LPDDR5 · 819 GB/s bandwidth ·
Moonshot · 1030.0B (active 32.0B) · MoE · model ctx up to 256K
No — Kimi-K2.6 at Q4 needs ≈ 570.7 GB even at 4K context, beyond the Mac Studio M3 Ultra 96GB's 96 GB LPDDR5. It would only run with heavy CPU/disk offload. FP16 needs ≈ 2067.4 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
570.7 GB
No
—
Q4
8K default
573.9 GB
No
—
Q4
32K
593.1 GB
No
—
FP16
4K
2064.2 GB
No
—
FP16
8K default
2067.4 GB
No
—
FP16
32K
2086.6 GB
No
—
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
566.5 GB
6.4 GB
1 GB
573.9 GB
96 GB
FP16
2060.0 GB
6.4 GB
1 GB
2067.4 GB
96 GB
Other GPUs that run Kimi-K2.6
No catalog GPU fully fits Kimi-K2.6 at Q4/8K — see the model page for offload estimates.