Model Profile

Kimi-K2-Instruct

Name: Kimi-K2-Instruct
Author: moonshotai

4,096 ctxOpen weights

Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.

Identity

ID: moonshotai/Kimi-K2-Instruct

Author: moonshotai

Origin: huggingface_catalog

Arch: unknown

Benchmark Coverage

Scored use cases: 12

Avg confidence: 14.6%

Evidence points: 38

Raw rows: 124

Weighted rows: 13

Catalog Metadata

Parameters: unknown

Context window: 4096

Downloads: 247,183

Some fit rows have limited benchmark evidence.

12 of 12 scored use cases have low confidence or thin contributor coverage.

Coverage Diagnostics

actively scored

Use-Case Scores

Total Measurements

124

Weighted Measurements

Weighted Sources

Raw Source Coverage

ugi_main 60galileo_agent_v2 34swe_bench_additional_public 12swe_bench_leaderboard 12swebench_bash_only_official 4swebench_verified_official 1

Weighted Source Coverage

galileo_agent_v2 10ugi_main 3

Best Use Cases for This Model

Use Case	Vertical	Score	Confidence	Evidence	Top Contributor
Claims summary use_case.ins.claims_summary	insurance	12.9%	16.3%	4	Galileo Agent Leaderboard v2: Insurance AC
Product positioning and messaging use_case.mkt.product_positioning	marketing_sales	12.7%	15.2%	3	Galileo Agent Leaderboard v2: Avg TSQ
Campaign brief use_case.mkt.campaign_brief	marketing_sales	12.7%	15.2%	3	Galileo Agent Leaderboard v2: Avg TSQ
Social post generation use_case.mkt.social_post_generation	marketing_sales	12.7%	15.2%	3	Galileo Agent Leaderboard v2: Avg TSQ
Kubernetes manifest generation use_case.sre.iac_k8s	devops_sre	12.0%	14.5%	2	Galileo Agent Leaderboard v2: Avg AC
Terraform generation use_case.sre.iac_terraform	devops_sre	12.0%	14.5%	2	Galileo Agent Leaderboard v2: Avg AC
Config debugging use_case.sre.config_debugging	devops_sre	12.0%	14.5%	2	Galileo Agent Leaderboard v2: Avg AC
Poetry and lyrics use_case.creative.poetry_lyrics	creative	11.9%	14.4%	4	UGI Leaderboard: Entertainment
Screenplay scene writing use_case.creative.screenplay_scene	creative	11.9%	14.4%	4	UGI Leaderboard: Entertainment
FNOL structuring use_case.ins.fnol_structuring	insurance	11.6%	14.6%	4	Galileo Agent Leaderboard v2: Insurance AC
Adult ERP roleplay (explicit) use_case.adult.erp_roleplay	adult	11.1%	13.5%	4	UGI Leaderboard: Entertainment
Personalized sales outreach use_case.mkt.sales_outreach_personalized	marketing_sales	11.1%	13.2%	3	Galileo Agent Leaderboard v2: Avg TSQ

Deployment Fit Calculator

Model

Kimi-K2-Instruct

moonshotai/Kimi-K2-Instruct

Hardware

Quantization: 4-bit

2-bit8-bit

Insufficient

Unknown parameter count. Cannot estimate deployment fit.

Required VRAM

~0.0GB

Est. Throughput

0.00 tok/s

Deployment Fit Matrix

GPU	4-bit	6-bit	8-bit
RTX 3060 12GB	Insufficient	Insufficient	Insufficient
RTX 3090 24GB	Insufficient	Insufficient	Insufficient
RTX 4090 24GB	Insufficient	Insufficient	Insufficient
Mac Studio M2 Ultra 192GB	Insufficient	Insufficient	Insufficient