Model field guide
Kimi-K2.6
No complete file set in the four requested quantizations was verified. Calculator estimates are unavailable for this model.
Total parameters1026.88B
Active parametersUnknown
Recorded context limit262,144
Architecturemoe
Verified 2026-10-22 · license metadata: other · commercial use: unknown (review the terms).
- KV cache is unknown or nonstandard; a complete context-memory estimate is unavailable.
- Mixture of experts: weight memory uses total parameters; a verified active-parameter count is unavailable.
- No complete supported GGUF quantization was verified in the searched public organization repositories.
- GGUF sizes cover language-model weights only; auxiliary vision projector/encoder memory is not included.
Actual files, not a size shortcut.
No requested quantization files verified.
The hardware picture.
A “fits” result checks estimated memory only. “Needs verification” preserves missing cache, vision, or placement information. All speed figures are estimated from the published bandwidth formula.
Field-level sources and verification dates
- id: Official source · verified 2026-10-22. Lowercase URL slug derived from the upstream repository ID; baseModel retains the exact Hugging Face identifier.
- name: Official source · verified 2026-10-22
- baseModel: Official source · verified 2026-10-22
- downloads: Official source · verified 2026-10-22
- tasks: Official source · verified 2026-10-22. Chat denotes a text-generating model, including base models that may require a chat template or instruction tuning. Code label is inferred from the repository model-family name. Vision uses pipeline metadata or vision_config.
- license: Official source · verified 2026-10-22
- commercialUse: Official source · verified 2026-10-22. Unknown or custom license, conflicting metadata, or unverified publisher. Review the linked license and applicable terms.
- license_url: Official source · verified 2026-10-22. Pinned license file confirmed in repository listing.
- architecture: Official source · verified 2026-10-22. Classification from model_type and expert/state-space configuration fields (kimi_k2); hybrid classification takes precedence over expert count.
- parametersB: Official source · verified 2026-10-22. Exact safetensors parameter total reported by the Hugging Face API, divided by 1e9.
- activeParametersB: Official source · verified 2026-10-22. Unknown: no reliable active-parameter count supplied. Total parameters are not substituted for active MoE parameters.
- contextLength: Official source · verified 2026-10-22. Configured maximum token positions; not a guarantee of runtime support or quality at that length. No speculative RoPE scaling applied.
- kvCache: Official source · verified 2026-10-22. Unknown: missing explicit KV shape or architecture uses hybrid, latent, sliding-window, or mixed-layer attention outside the simple estimator.