Kimi K3 Models — Hardware Requirements
3 Kimi K3 models from Moonshot AI and the community, from the smallest that runs in 2.2 GB of VRAM at Q4 up to 2780.1B parameters. Every row links to full quantization tables and GPU compatibility.
All Kimi K3 Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Kimi K3 DSpark | 2.2B | 2.2 GB | 1049K | ||
| Kimi K3 | 2779.9B | 1670.0 GB | 1049K | ||
| Kimi K3.1 Pro | 2780.1B | 1712.1 GB | 1049K |
How Kimi K3 Compares — llmrun Composite Score
Kimi K3.1 Pro is the highest-scoring Kimi K3 model with an llmrun Composite Score of 142.8 — #1 among 106 open models. The top proprietary model, Gemini 4 Carbon, scores 158.6. Click a model to see its full benchmark breakdown.
Gemini 4 Carbon · proprietary158.6
GPT 6 Astra · proprietary156.2
Claude Opus 5.5 · proprietary153.0
GPT 6.1 Sol · proprietary151.7
GPT 6.1 Terra · proprietary150.1
Kimi K3.1 Pro142.8
MiMo V2.6 Pro RL133.3
Kimi K3132.7
MiMo V2.6 Flash RL131.9
GLM 5.3130.1
DeepSeek V4.1 Flash129.4
DeepSeek V4 Pro 0813129.2
Step 5 Preview128.0
Frequently Asked Questions
- How much VRAM do I need to run a Kimi K3 model?
- The smallest Kimi K3 model, Kimi K3 DSpark, runs from 2.2 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 1.3 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which Kimi K3 models can I run on a 16 GB GPU?
- 1 of 3 Kimi K3 models fit in 16 GB of VRAM at Q4_K_M, including Kimi K3 DSpark.
- What is the most popular Kimi K3 model to run locally?
- Kimi K3 is the most downloaded Kimi K3 model in local-friendly quantized formats. It runs from 1670.0 GB of VRAM at Q4_K_M.
- How do Kimi K3 models score on benchmarks?
- Kimi K3.1 Pro leads the family with an llmrun Composite Score of 142.8, ranking #1 among 106 open models, while the top proprietary model, Gemini 4 Carbon, scores 158.6. See the comparison chart above for the full standings.