LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3 4B Kimi2.5 Reasoning Distilled by khazarai

 »  All LLMs  »  khazarai  »  Qwen3 4B Kimi2.5 Reasoning Distilled   URL Share it on

  1153   

Qwen3 4B Kimi2.5 Reasoning Distilled is an open-source language model by khazarai. Features: 4b LLM, VRAM: 8.1GB, Context: 256K, License: apache-2.0.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b-think...   Conversational Dataset:khazarai/kimi-2.5-high...   En   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled 
Qwen3 4B Kimi2.5 Reasoning Distilled (khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled)
🌟 Advertise your project 🚀

Qwen3 4B Kimi2.5 Reasoning Distilled Parameters and Internals

LLM NameQwen3 4B Kimi2.5 Reasoning Distilled
Repository 🤗https://huggingface.co/khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled 
Base Model(s)  Qwen3 4B Thinking 2507   Qwen/Qwen3-4B-Thinking-2507
Model Size4b
Required VRAM8.1 GB
Updated2026-04-11
Maintainerkhazarai
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3 4B Kimi2.5 Reasoning Distilled

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Thinking 2507256K / 8.1 GB1676918575
GRPO 4 70256K / 8.1 GB200
Qwen3 4B Instruct 2507256K / 8.1 GB1473674320
QED Nano256K / 8.1 GB681686
Jan Code 4B256K / 8.9 GB227072
Jan V1 4B256K / 8.1 GB108354353
AgentCPM Explore256K / 8.9 GB129328
Lightning 4B256K / 8.1 GB136
...en3.6 Plus Reasoning Distilled256K / 8.1 GB10873
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB71535873
Note: green Score (e.g. "73.2") means that the model is better than khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled.

Rank the Qwen3 4B Kimi2.5 Reasoning Distilled Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer