Kimi K3
moonshotaiothertextvision

Kimi K3

Updated Jul 30, 2026
Parameters
2779.9B
Context
1,048,576
License
other
Updated
Jul 30, 2026

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

57.1

AA Index

Coding

76.2

AA Index

Agentic

50.1

AA Index

Intelligence Index - Kimi K3 vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 5 (max)
60.7
closed
Claude Fable 5 (with fallback)
59.9
closed
GPT-5.6 Sol (max)
58.9
closed
Kimi K3
57.1
open
GPT-5.6 Terra (max)
55
closed
Grok 4.5 (high)
53.8
closed
GLM-5.2
51.1
open

Coding Index comparison

GPT-5.6 Sol (xhigh)
78.3
closed
Claude Opus 5 (max)
78
closed
GPT-5.6 Terra (max)
76.7
closed
Claude Fable 5 (with fallback)
76.5
closed
Kimi K3
76.2
open
Grok 4.5 (high)
72.4
closed
GLM-5.2
68.8
open

Agentic Index comparison

Claude Opus 5 (max)
55.3
closed
GPT-5.6 Sol (max)
54
closed
Claude Fable 5 (with fallback)
52.8
closed
Kimi K3
50.1
open
GPT-5.6 Terra (max)
47.4
closed
Claude Sonnet 5 (max)
46.7
closed
GLM-5.2
43.1
open

Benchmark data from Artificial Analysis · updated 2026-07-30.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA93.5

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Too big for 24 GB at any quant
0 of 4 quantizations fit Kimi K3 with real runtime overhead.
Q4_K_M
1612 GB
Q5_K_M
1974 GB
Q8_0
2974 GB
FP16
5560 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve moonshotai/Kimi-K3

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

Kimi K3 is a 2779.9B-parameter other model from Kimi. It scores 57.1 on the Artificial Analysis Intelligence Index (coding 76.2). At Q4_K_M it needs roughly 1612 GB of VRAM, placing it in the 48 GB+ / multi-GPU hardware tier.

Benchmarks

Artificial Analysis Intelligence Index - Kimi K3 vs. leading closed models:

ModelIntelligenceCodingGPQA
Kimi K357.176.293.5
Claude Opus 5 (max)60.77893.2
Claude Fable 5 (with fallback)59.976.592.6
GPT-5.6 Sol (max)58.977.494.1
GPT-5.6 Terra (max)5576.792.5
Grok 4.5 (high)53.872.493.1

Source: Artificial Analysis (2026-07-30).

Popularity

Kimi K3 has 99,214 downloads in the last month on HuggingFace and 8,653 likes.

Frequently asked

Quick answers to common questions

How much VRAM does Kimi K3 need?

Kimi K3 with 2779.9B parameters needs approximately 1612 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is Kimi K3 better than other moonshotai models?

Kimi K3 has 2779.9B parameters with 1,048,576 context - a strong choice for general use.

What license is Kimi K3 under?

Kimi K3 is released under the other license, making it suitable for most commercial and personal projects.

What hardware runs Kimi K3 well?

With 2779.9B parameters, Kimi K3 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for Kimi K3?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1974 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can Kimi K3's context window handle?

Kimi K3 supports a 1,048,576-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with Kimi K3?

Kimi K3 competes with other 1390B–4170B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.