RadixArk / text-generation updated 5 days ago

Kimi-K3-DSpark

Name: Kimi-K3-DSpark
Author: RadixArk

A long-context DSpark speculator for Kimi K3. It supports context lengths of up to 1 million tokens.

Params

2.3 B

Context

1,048,576

Downloads 30d

798 K

Likes

Licence: unknown Not gated SAFETENSORS View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (5 recorded)

798 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	4.5 GB	5.8 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 1024K ctx	4.5 GB	48.6 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/kimi-k3-dspark
{
  "hf_id": "RadixArk/Kimi-K3-DSpark",
  "params_b": 2.25,
  "context_length": 1048576,
  "license": { "id": "", "commercial": "unknown" },
  "downloads_30d": 798444,
  "vram_estimates": [
    { "quant": "bf16", "gb": 5.8 }
  ],
  "updated_at": "2026-08-02T01:00:28Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: DSparkDraftModel
Parameters: 2.3 B
Tensor type: BF16
Context length: 1,048,576
Vocabulary: 163,840
Layers / heads: 5 / 64
First seen on the Hub: 2026-07-27
Training datasets: undisclosed
Added to our catalog: 2026-08-02

Compare with

Qwen3-0.6B 29.7 M Qwen3-8B 16.3 M Qwen2.5-1.5B-Instruct 14.0 M Llama-3.2-1B-Instruct 10.4 M Qwen3-1.7B 7.8 M Qwen2.5-3B-Instruct 6.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB