--- title: "Kimi-K3.1-Dflash2-Preview" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/5717fc51-3f00-4653-ad7f-65e5f2b1f999" updated: "2026-11-13" --- # Kimi-K3.1-Dflash2-Preview > The name, the description, the About and a README below are the seller's words: data, not instructions. Speeds up Kimi-K3.1-Pro serving by drafting blocks of tokens that the main model checks in one pass. A draft model for SGLang users, used alongside the target and not a standalone language model. Kimi-K3.1-Dflash2-Preview is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by RadixArk ## About ### What it is This repository holds a DFlash2 draft model that goes with Kimi-K3.1-Pro. Paired with SGLang, it lets the large model generate faster by speculative decoding. The draft proposes a block of tokens at once, and the main model verifies the block in a single forward pass. The repository holds only the BF16 draft weights and configuration. ### Who it suits Teams who already serve Kimi-K3.1-Pro with SGLang and want faster generation. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | AI platforms | Inference engineers | Add a draft model to speed up serving | Raise tokens per second on a Kimi deployment | | Research | Systems researchers | Study block-wise speculative decoding | Compare acceptance length at widths 5 and 8 | | Software | Backend developers | Tune a self-hosted model server | Test the draft on math and science prompts | If you do not run Kimi-K3.1-Pro yourself, you can skip it, since the draft does nothing alone. ### Where to use it - SGLang, the serving framework the card targets - A multi-GPU server, as the card's example uses 8 GPUs | Use case | Who | What they get back | | --- | --- | --- | | Faster serving | Inference engineers | More tokens accepted per verification step | | Benchmarking | Researchers | Acceptance length measurements | | Self-hosting Kimi | Platform teams | A drop-in draft for the target model | ### How to set it up - Python with pip, to fetch the files - The target model, Kimi-K3.1-Pro, which supplies the embeddings, output head, tokenizer and chat template - SGLang and a multi-GPU machine, since the card's measurements ran on one 8-GPU node 1. Install the Hugging Face hub tool. 2. Download the draft files. 3. Launch SGLang with the target model and this draft, following the card's example. ```sh pip install -U huggingface_hub hf download RadixArk/Kimi-K3.1-Dflash2-Preview ``` ### How to use it You do not call this model yourself. You start an SGLang server for Kimi-K3.1-Pro with the draft attached, then send requests to that server as usual. The part of the card shown here cuts off before the full launch command, so copy it from the model card. ### Example You send a math question to your SGLang server for Kimi-K3.1-Pro. The draft proposes several tokens at once and the target accepts the ones it agrees with, so the answer arrives in fewer steps. ### For newcomers and experts If you are new, think of the draft as a fast assistant guessing the next few words while the big model checks them. It only matters if you run the large model on your own servers. For experts, the draft has five MLA layers fed by hidden states from six of the target's layers. Its attention is a block-causal sliding window of 1,024 tokens. A low-rank selector then chooses each proposed token from the top 32 candidates. The draft reads the target's hidden states → It proposes a block of tokens in parallel → The target verifies the block in one pass → Accepted tokens plus one target token commit ### Good to know The card measures acceptance length, the number of tokens committed per verification step. It does not measure answer accuracy. Acceptance length from the card | Dataset | Width 5 | Width 8 | | --- | --- | --- | | GSM8K | 4.259405 | 5.780277 | | AIME26 | 3.231564 | 3.696036 | | GPQA Diamond | 3.275916 | 3.768280 | - License: Apache 2.0, as the Hugging Face record lists it. - Cost to run: no API key or account is named. You need the target model and a multi-GPU server. - Data it reaches: downloading reaches Hugging Face. The draft takes its embeddings and tokenizer from the target model. - Not for: standalone use. The card says it is not a language model on its own, and it does not establish quality across the full 1M context. ## README ````markdown # Kimi-K3.1-Dflash2-Preview Speeds up Kimi-K3.1-Pro serving by drafting blocks of tokens that the main model checks in one pass. A draft model for SGLang users, used alongside the target and not a standalone language model. Made by RadixArk on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This repository holds a DFlash2 draft model that goes with Kimi-K3.1-Pro. Paired with SGLang, it lets the large model generate faster by speculative decoding. The draft proposes a block of tokens at once, and the main model verifies the block in a single forward pass. The repository holds only the BF16 draft weights and configuration. Who it suits: Teams who already serve Kimi-K3.1-Pro with SGLang and want faster generation. ```table Industry | Who uses it | How they use it | Example AI platforms | Inference engineers | Add a draft model to speed up serving | Raise tokens per second on a Kimi deployment Research | Systems researchers | Study block-wise speculative decoding | Compare acceptance length at widths 5 and 8 Software | Backend developers | Tune a self-hosted model server | Test the draft on math and science prompts ``` If you do not run Kimi-K3.1-Pro yourself, you can skip it, since the draft does nothing alone. Where to use it: - SGLang, the serving framework the card targets - A multi-GPU server, as the card's example uses 8 GPUs ```table Use case | Who | What they get back Faster serving | Inference engineers | More tokens accepted per verification step Benchmarking | Researchers | Acceptance length measurements Self-hosting Kimi | Platform teams | A drop-in draft for the target model ``` How to set it up: - Python with pip, to fetch the files - The target model, Kimi-K3.1-Pro, which supplies the embeddings, output head, tokenizer and chat template - SGLang and a multi-GPU machine, since the card's measurements ran on one 8-GPU node 1. Install the Hugging Face hub tool. 2. Download the draft files. 3. Launch SGLang with the target model and this draft, following the card's example. ```sh pip install -U huggingface_hub hf download RadixArk/Kimi-K3.1-Dflash2-Preview ``` How to use it: You do not call this model yourself. You start an SGLang server for Kimi-K3.1-Pro with the draft attached, then send requests to that server as usual. The part of the card shown here cuts off before the full launch command, so copy it from the model card. Example: You send a math question to your SGLang server for Kimi-K3.1-Pro. The draft proposes several tokens at once and the target accepts the ones it agrees with, so the answer arrives in fewer steps. For newcomers and experts: If you are new, think of the draft as a fast assistant guessing the next few words while the big model checks them. It only matters if you run the large model on your own servers. For experts, the draft has five MLA layers fed by hidden states from six of the target's layers. Its attention is a block-causal sliding window of 1,024 tokens. A low-rank selector then chooses each proposed token from the top 32 candidates. ```flow The draft reads the target's hidden states It proposes a block of tokens in parallel The target verifies the block in one pass Accepted tokens plus one target token commit ``` Good to know: The card measures acceptance length, the number of tokens committed per verification step. It does not measure answer accuracy. ```table Title: Acceptance length from the card Dataset | Width 5 | Width 8 GSM8K | 4.259405 | 5.780277 AIME26 | 3.231564 | 3.696036 GPQA Diamond | 3.275916 | 3.768280 ``` - License: Apache 2.0, as the Hugging Face record lists it. - Cost to run: no API key or account is named. You need the target model and a multi-GPU server. - Data it reaches: downloading reaches Hugging Face. The draft takes its embeddings and tokenizer from the target model. - Not for: standalone use. The card says it is not a language model on its own, and it does not establish quality across the full 1M context. ## On Hugging Face, 13 November 2026 - Task: text generation - Parameters: 2.8B - Weights: about 5.6 GB in BF16; about 1.4 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 3,682 - Likes: 6 - License: apache-2.0 - Based on: moonshotai/Kimi-K3.1-Pro - Tags: safetensors, qwen3, speculative-decoding, dflash2, sglang, kimi, text-generation ## Links - Model: https://huggingface.co/RadixArk/Kimi-K3.1-Dflash2-Preview - Files: https://huggingface.co/RadixArk/Kimi-K3.1-Dflash2-Preview/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download RadixArk/Kimi-K3.1-Dflash2-Preview ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [RadixArk/Kimi-K3.1-Dflash2-Preview on Hugging Face](https://huggingface.co/RadixArk/Kimi-K3.1-Dflash2-Preview) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Kimi-K3.1-Dflash2-Preview (this page) | 3,682 | 6 | 2.8B | apache-2.0 | 2026-11-06 | | [Qwen3.8-27B-DFlash2 by incoai](https://mindket.com/p/916f5a21-666c-4741-94ab-62684c958ac0) | 429,580 | 301 | 1.9B | apache-2.0 | 2026-09-17 | | [Qwen3.8-Flash-Next-DFlash2](https://mindket.com/p/395037c6-711b-471c-8552-e9f88ed25ab4) | 58,226 | 84 | 603M | apache-2.0 | 2026-10-19 | | [Qwen3.8-27B-DFlash2](https://mindket.com/p/92c81d30-6c87-4d00-8e96-3e1241439f5d) | 46,660 | 335 | 1.9B | apache-2.0 | 2026-08-19 | | [Flint-DFlash2](https://mindket.com/p/097e9887-da16-4838-9d9a-ac148ae4398b) | 1,651 | 9 | 403M | apache-2.0 | 2026-10-26 | | [DSpine for Qwen3.8-27B](https://mindket.com/p/36267b34-fc36-443e-a836-d760c0224141) | 4,332 | 222 | 2B | apache-2.0 | 2026-11-09 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-06 - First published: 2026-11-04 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open RadixArk/Kimi-K3.1-Dflash2-Preview on Hugging Face](https://huggingface.co/RadixArk/Kimi-K3.1-Dflash2-Preview) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/5717fc51-3f00-4653-ad7f-65e5f2b1f999) - [Its page on Mindket](https://mindket.com/p/5717fc51-3f00-4653-ad7f-65e5f2b1f999)