Kimi K3

moonshotai/Kimi-K3

Parameters

2800B

Context

1024K

Downloads

1.6M

Likes

10.5K

Architecture

moe_transformer

View on HuggingFace

GPU Requirements

VRAM / RAM / disk estimates by quantization and usage scenario

QuantizationMinimumRecommendedProduction
FP1616bit
6601.1 GB
RAM 9901.6 · Disk 8175.0
6903.1 GB
RAM 10354.7 · Disk 8201.0
7218.9 GB
RAM 10828.3 · Disk 8240.0
FP88bit
3302.3 GB
RAM 4953.5 · Disk 4107.0
3454.4 GB
RAM 5181.7 · Disk 4133.0
3620.2 GB
RAM 5430.4 · Disk 4172.0
INT88bit
3302.3 GB
RAM 4953.5 · Disk 4107.0
3454.4 GB
RAM 5181.7 · Disk 4133.0
3620.2 GB
RAM 5430.4 · Disk 4172.0
AWQ4bit
1714.8 GB
RAM 2572.2 · Disk 2149.3
1794.8 GB
RAM 2692.1 · Disk 2175.3
1888.4 GB
RAM 2832.6 · Disk 2214.3
GPTQ4bit
1735.4 GB
RAM 2603.1 · Disk 2174.7
1816.3 GB
RAM 2724.5 · Disk 2200.7
1910.9 GB
RAM 2866.3 · Disk 2239.7
GGUF4bit
1776.7 GB
RAM 2665.0 · Disk 2225.6
1859.4 GB
RAM 2789.1 · Disk 2251.6
1955.9 GB
RAM 2933.8 · Disk 2290.6

GPU Recommendations

⚠️ No single GPU fits — check multi-GPU options

This model needs more VRAM than a single GPU can provide. Cluster options below (may still be short):(1794.76 GB VRAM)

8× B200

1440 GB · short by 354.76 GB

$24,102/mo

Deploy on vast ↗

8× H200 SXM

1128 GB · short by 666.76 GB

$20,440/mo

8× A100 80GB

640 GB · short by 1154.76 GB

$7,008/mo

Deploy on vast ↗

8× H100 SXM

640 GB · short by 1154.76 GB

$9,357/mo

Deploy on vast ↗

8× RTX A6000

384 GB · short by 1410.76 GB

$1,678/mo

Deploy on vast ↗

8× L40S

384 GB · short by 1410.76 GB

$2,727/mo

Deploy on vast ↗

💬 Community — real deployment experience

0 Articles · 0 Benchmarks

View Community →
AmciHub

AI Model Deployment & Compute Intelligence — analyze AI model requirements, GPU performance, cloud pricing and deployment costs to find the right deployment solution.

© 2026 AmciHub. All rights reserved. Model → Requirement → GPU → Benchmark → Cloud → Cost → Recommendation