Kimi-K3-DSpark
RadixArkOpen Weightstext

Kimi-K3-DSpark

Updated Nov 9, 2026
Parameters
2.2B
Context
1,048,576
License
Open Weights
Q4 GGUF
1.33 GB
Updated
Nov 9, 2026

Q4 GGUF download: Anbeeld/Kimi-K3-DSpark-GGUF - 1.33 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.

Will it run on your hardware?

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

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit Kimi-K3-DSpark with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
2 GB
Q8_0
2 GB
FP16
4 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 RadixArk/Kimi-K3-DSpark

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

Deep dive

Notes, sources, and the full write-up

Kimi-K3-DSpark is a 2.2B-parameter open-weight model from RadixArk. At Q4_K_M it needs roughly 1 GB of VRAM, placing it in the CPU / ≤4 GB hardware tier.

PopularityLink to this section

Kimi-K3-DSpark has 1,139,979 downloads in the last month on HuggingFace and 47 likes.

Frequently asked

Quick answers to common questions

How much VRAM does Kimi-K3-DSpark need?

Kimi-K3-DSpark with 2.2B parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is Kimi-K3-DSpark better than other RadixArk models?

Kimi-K3-DSpark has 2.2B parameters with 1,048,576 context - a strong choice for general use.

What license is Kimi-K3-DSpark under?

Kimi-K3-DSpark is released under the Open Weights license, making it suitable for most commercial and personal projects.

What hardware runs Kimi-K3-DSpark well?

With 2.2B parameters, Kimi-K3-DSpark 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-DSpark?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~2 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can Kimi-K3-DSpark's context window handle?

Kimi-K3-DSpark 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-DSpark?

Kimi-K3-DSpark competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec