mlx-community / text-generation updated 6 months ago

Kimi-K2.5

Name: Kimi-K2.5
Author: mlx-community

This model mlx-community/Kimi-K2.5 was converted to MLX format from moonshotai/Kimi-K2.5 using mlx-lm version 0.30.5 (slightly modified).

Params

1,026.4 B

Context

—

Downloads 30d

188 K

Likes

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

190 K185 K

Jul 28Jul 31Aug 3Aug 6

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	u32	657.6 GB	877.8 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-k2-5
{
  "hf_id": "mlx-community/Kimi-K2.5",
  "params_b": 1026.41,
  "context_length": null,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 187629,
  "vram_estimates": [
    { "quant": "u32", "gb": 877.8 }
  ],
  "updated_at": "2026-07-28T18:08:18Z"
}

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

Specifications

Architecture: KimiK25ForConditionalGeneration
Parameters: 1,026.4 B
Tensor type: U32
Licence: other
First seen on the Hub: 2026-01-27
Base model: Kimi-K2.5
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Kimi-K2.5 moonshotai 966 K

Compare with

DeepSeek-R1 9.9 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M DeepSeek-V4-Pro 1.6 M DeepSeek-V3.2 1.2 M GLM-5-FP8 1.2 M

Appears in

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