Can you run Kimi K2.5 locally?
Kimi family · Jan 2026 · 1.03T parameters · Hugging Face model card
Kimi K2.5 is a mixture-of-experts model activating 8 of 384 experts per token released with open weights on Hugging Face: 1026.88B total parameters, a 262,144-token context window, other license. Running it locally needs roughly 768 GB of memory at Q4-class quantization (calculated) — multi-GPU server or large-unified-memory territory. Measured local speeds: not yet published here; we list unknowns as unknowns.
Minimum: 768 GB+ memory (Q4-class, calculated) · Recommended: 1,024 GB+ for comfortable context headroom (Q4-class, calculated)
How much VRAM does Kimi K2.5 need at each quantization?
Kimi K2.5 needs 677.7 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.
| Quantization | Bits / weight | Weights only | Total + KV @4k ctx | Total + KV @32k ctx |
|---|---|---|---|---|
| Q4_K_M | 4.8 | 616.1 GB | 677.7 GB | 677.7 GB |
| Q5_K_M | 5.7 | 731.7 GB | 804.8 GB | 804.8 GB |
| Q6_K | 6.6 | 847.2 GB | 931.9 GB | 931.9 GB |
| Q8_0 | 8.5 | 1,091.1 GB | 1,200.2 GB | 1,200.2 GB |
| FP16 | 16 | 2,053.8 GB | 2,259.1 GB | 2,259.1 GB |
Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (not applicable to this architecture). Source: HF-verified 2026-09-12 via api (repo safetensors + config.json); VRAM figures are documented calculations, not measurements
Which GPUs can run Kimi K2.5 locally?
At Q4_K_M with a 4k context, Kimi K2.5 needs 677.7 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.
No single consumer GPU in our database runs Kimi K2.5 at Q4_K_M. The 677.7 GB requirement exceeds every listed consumer card; see the Mac and data center options above and below.