Kimi-K2.5-MLX-2.8bit

1.4K
—
by
spicyneuron
Language Model
OTHER
2.8B params
New
1K downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
7GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
3GB+ RAM

Training Data Analysis

🔵 Good (6.0/10)

Researched training datasets used by Kimi-K2.5-MLX-2.8bit with quality assessment

Specialized For

general
multilingual

Training Datasets (1)

c4
🔵 6/10
general
multilingual
Key Strengths
  • •Scale and Accessibility: 750GB of publicly available, filtered text
  • •Systematic Filtering: Documented heuristics enable reproducibility
  • •Language Diversity: Despite English-only, captures diverse writing styles
Considerations
  • •English-Only: Limits multilingual applications
  • •Filtering Limitations: Offensive content and low-quality text remain despite filtering

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

Usagebash
# Start server at http://localhost:8080/v1/chat/completions
uvx --from mlx-lm --with tiktoken \
  mlx_lm.server \
    --host 127.0.0.1 --port 8080 \
    --trust-remote-code \
    --model spicyneuron/Kimi-K2.5-MLX-2.8bit

# Kimi K2.5 requires tiktoken + remote code for the tokenizer

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.