Kimi K2.6 DFlash is an open-source language model by nvidia. Features: 3.5b LLM, VRAM: 7GB, Context: 256K, License: other, LLM Explorer Score: 0.3.
Base model:finetune:moonshotai... Base model:moonshotai/kimi-k2.... Dflash Kimi-k2.6 Model optimizer Modelopt Nvidia Qwen3 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/nvidia/Kimi-K2.6-DFlash
Kimi K2.6 DFlash Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Kimi K2.6 DFlash Parameters and Internals
| LLM Name | Kimi K2.6 DFlash |
| Repository 🤗 | https://huggingface.co/nvidia/Kimi-K2.6-DFlash |
| Base Model(s) | |
| Model Size | 3.5b |
| Required VRAM | 7 GB |
| Updated | 2026-07-02 |
| Maintainer | nvidia |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | DFlashDraftModel |
| License | other |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Vocabulary Size | 163840 |
| Torch Data Type | bfloat16 |
Rank the Kimi K2.6 DFlash 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! 🌟
What open-source LLMs or SLMs are you in search of? 54724 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a