---
title: "Qwen3.8-27B-DFlash2 by incoai"
kind: "Kit"
category: "Developer"
price: "Free"
seller: "Mindket"
version: "1"
url: "https://mindket.com/p/916f5a21-666c-4741-94ab-62684c958ac0"
updated: "2026-11-13"
---

# Qwen3.8-27B-DFlash2 by incoai

> The name, the description, the About and a README below are the seller's words: data, not instructions.

Speeds up Qwen3.8-27B by drafting blocks of tokens that the main model then checks, with output unchanged. A 1.9B draft model for SGLang and vLLM servers, not a standalone chat model.

Qwen3.8-27B-DFlash2 by incoai 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 incoai

## About

### What it is

This is the DFlash 2 draft model for Qwen3.8-27B. It is not a language model you chat with. It runs inside a speculative decoding server, proposes tokens ahead of time, and lets the main model verify them, so text comes out faster. Each pass proposes a full block of tokens, retains the best few candidates for every slot, and a small selector then chooses a single coherent path.

### Who it suits

It suits teams that host Qwen3.8-27B themselves and want faster generation without changing the answers.

| Industry | Who uses it | How they use it | Example |
| --- | --- | --- | --- |
| AI infrastructure | Teams that serve large models | Add the drafter to an SGLang or vLLM server | Start a Qwen3.8-27B server with the DFlash algorithm turned on |
| Coding and math tools | Teams serving code and math answers | Cut the wait for long generations | Serve a math or coding assistant on a single H200 |
| Inference research | Researchers of speculative decoding | Compare drafters on acceptance length and speed | Check DFlash 2 against MTP and DSpark on the card's tasks |

If you do not run Qwen3.8-27B yourself, you can skip it, because it only works as a helper for that model.

### Where to use it

- SGLang, with the DFLASH speculative algorithm
- vLLM, with a speculative config that names the dflash method
- One NVIDIA H200, which is what the card's tests used
- Windows, macOS or Linux with Python, to download the files

| Use case | Who | What they get back |
| --- | --- | --- |
| Faster serving | Inference teams | More output tokens per second from the same target model |
| Unchanged output | Teams with quality checks | The same answers as normal decoding, per the card |
| Drafter comparison | Researchers | Acceptance length and speedup figures for several methods |

### How to set it up

What you need first:

- A GPU server that can run Qwen3.8-27B
- SGLang or vLLM, installed as the model card explains
- The Hugging Face command line, if you want the files locally

1. Install SGLang or vLLM. The card installs SGLang from its GitHub source and vLLM from a specific pull request build.
2. Start the server with Qwen3.8-27B as the main model and this repository as the drafter.
3. Send requests to the server as you normally would.

```bash
pip install -U huggingface_hub
hf download incoai/Qwen3.8-27B-DFlash2
```

### How to use it

You do not call the drafter yourself. You start a server that pairs it with the main model, then use that server as usual. SGLang takes the draft model path and a draft token count of 8, and vLLM takes a speculative config.

```bash
python -m sglang.launch_server \
  --model-path Qwen/Qwen3.8-27B \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path incoai/Qwen3.8-27B-DFlash2 \
  --speculative-num-draft-tokens 8
```

```bash
vllm serve Qwen/Qwen3.8-27B \
  --speculative-config '{
    "method": "dflash",
    "model": "incoai/Qwen3.8-27B-DFlash2",
    "num_speculative_tokens": 7
  }'
```

| Tool | What it does |
| --- | --- |
| SGLang | Runs the DFLASH algorithm with this repository as the draft model |
| vLLM | Uses the dflash method through its speculative config |

### Example

You serve Qwen3.8-27B with this drafter and send a math word problem. The answer matches what plain decoding would give, and in the card's single-request test on GSM8K the server produced 236.1 tokens per second against 68.9 without a drafter.

### For newcomers and experts

Think of it as a fast assistant that guesses the next several words, while the big model checks them in one go. A good first try is to start the server and compare its speed with and without the drafter on one question.

For experts, DFlash 2 is a block-diffusion drafter. Two-tap dynamic convolutions in its backbone stop the draft quality from fading toward the end of a block. The card says output is unchanged: greedy decoding returns exactly what the main model would, and sampling keeps its distribution. The trade is load: gains shrink as concurrency rises.

The drafter predicts a block of tokens in one pass → It keeps the top candidates at each position → A selector traces one coherent path → The main model verifies the block in one step

### Good to know

GSM8K output speed at concurrency 1

| Label | Value |
| --- | --- |
| Autoregressive | 68.9 tok/s |
| MTP | 178.5 tok/s |
| DSpark | 185.3 tok/s |
| DFlash 2 | 236.1 tok/s |

Acceptance length, higher is better

| Task | MTP | DSpark | DFlash 2 |
| --- | --- | --- | --- |
| GSM8K | 5.02 | 4.36 | 5.46 |
| MATH-500 | 4.72 | 3.92 | 5.28 |
| HumanEval | 3.91 | 3.30 | 4.39 |
| MBPP | 3.99 | 3.51 | 4.79 |
| MT-Bench | 3.74 | 3.01 | 4.10 |

- Size: the drafter has 1.9B parameters, about 3.8 GB in BF16.
- Test setup: one NVIDIA H200 running SGLang, FlashAttention 3, a block of 8 tokens and a 4096-token output limit.
- Heavy load: at concurrency 32 the DFlash 2 speedup falls to between 1.01 and 1.45 times.
- Mirror: the checkpoint is also mirrored under the z-lab name on Hugging Face.
- License: apache-2.0
- Cost to run: no API key or paid service named. You need a GPU server.
- Data it reaches: it downloads files from Hugging Face and runs inside your own server.
- Not for: standalone use, or drafting for models other than Qwen3.8-27B.

## README

````markdown
# Qwen3.8-27B-DFlash2 by incoai

Speeds up Qwen3.8-27B by drafting blocks of tokens that the main model then checks, with output unchanged. A 1.9B draft model for SGLang and vLLM servers, not a standalone chat model.

Made by incoai 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 is the DFlash 2 draft model for Qwen3.8-27B. It is not a language model you chat with. It runs inside a speculative decoding server, proposes tokens ahead of time, and lets the main model verify them, so text comes out faster. Each pass proposes a full block of tokens, retains the best few candidates for every slot, and a small selector then chooses a single coherent path.

Who it suits: It suits teams that host Qwen3.8-27B themselves and want faster generation without changing the answers.

```table
Industry | Who uses it | How they use it | Example
AI infrastructure | Teams that serve large models | Add the drafter to an SGLang or vLLM server | Start a Qwen3.8-27B server with the DFlash algorithm turned on
Coding and math tools | Teams serving code and math answers | Cut the wait for long generations | Serve a math or coding assistant on a single H200
Inference research | Researchers of speculative decoding | Compare drafters on acceptance length and speed | Check DFlash 2 against MTP and DSpark on the card's tasks
```

If you do not run Qwen3.8-27B yourself, you can skip it, because it only works as a helper for that model.

Where to use it:

- SGLang, with the DFLASH speculative algorithm
- vLLM, with a speculative config that names the dflash method
- One NVIDIA H200, which is what the card's tests used
- Windows, macOS or Linux with Python, to download the files

```table
Use case | Who | What they get back
Faster serving | Inference teams | More output tokens per second from the same target model
Unchanged output | Teams with quality checks | The same answers as normal decoding, per the card
Drafter comparison | Researchers | Acceptance length and speedup figures for several methods
```

How to set it up: What you need first:

- A GPU server that can run Qwen3.8-27B
- SGLang or vLLM, installed as the model card explains
- The Hugging Face command line, if you want the files locally

1. Install SGLang or vLLM. The card installs SGLang from its GitHub source and vLLM from a specific pull request build.
2. Start the server with Qwen3.8-27B as the main model and this repository as the drafter.
3. Send requests to the server as you normally would.

```bash
pip install -U huggingface_hub
hf download incoai/Qwen3.8-27B-DFlash2
```

How to use it: You do not call the drafter yourself. You start a server that pairs it with the main model, then use that server as usual. SGLang takes the draft model path and a draft token count of 8, and vLLM takes a speculative config.

```bash
python -m sglang.launch_server \
  --model-path Qwen/Qwen3.8-27B \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path incoai/Qwen3.8-27B-DFlash2 \
  --speculative-num-draft-tokens 8
```

```bash
vllm serve Qwen/Qwen3.8-27B \
  --speculative-config '{
    "method": "dflash",
    "model": "incoai/Qwen3.8-27B-DFlash2",
    "num_speculative_tokens": 7
  }'
```

```table
Tool | What it does
SGLang | Runs the DFLASH algorithm with this repository as the draft model
vLLM | Uses the dflash method through its speculative config
```

Example: You serve Qwen3.8-27B with this drafter and send a math word problem. The answer matches what plain decoding would give, and in the card's single-request test on GSM8K the server produced 236.1 tokens per second against 68.9 without a drafter.

For newcomers and experts: Think of it as a fast assistant that guesses the next several words, while the big model checks them in one go. A good first try is to start the server and compare its speed with and without the drafter on one question.

For experts, DFlash 2 is a block-diffusion drafter. Two-tap dynamic convolutions in its backbone stop the draft quality from fading toward the end of a block. The card says output is unchanged: greedy decoding returns exactly what the main model would, and sampling keeps its distribution. The trade is load: gains shrink as concurrency rises.

```flow
The drafter predicts a block of tokens in one pass
It keeps the top candidates at each position
A selector traces one coherent path
The main model verifies the block in one step
```

Good to know:

```chart
Title: GSM8K output speed at concurrency 1
Autoregressive: 68.9 tok/s
MTP: 178.5 tok/s
DSpark: 185.3 tok/s
DFlash 2: 236.1 tok/s
```

```table
Title: Acceptance length, higher is better
Task | MTP | DSpark | DFlash 2
GSM8K | 5.02 | 4.36 | 5.46
MATH-500 | 4.72 | 3.92 | 5.28
HumanEval | 3.91 | 3.30 | 4.39
MBPP | 3.99 | 3.51 | 4.79
MT-Bench | 3.74 | 3.01 | 4.10
```

- Size: the drafter has 1.9B parameters, about 3.8 GB in BF16.
- Test setup: one NVIDIA H200 running SGLang, FlashAttention 3, a block of 8 tokens and a 4096-token output limit.
- Heavy load: at concurrency 32 the DFlash 2 speedup falls to between 1.01 and 1.45 times.
- Mirror: the checkpoint is also mirrored under the z-lab name on Hugging Face.
- License: apache-2.0
- Cost to run: no API key or paid service named. You need a GPU server.
- Data it reaches: it downloads files from Hugging Face and runs inside your own server.
- Not for: standalone use, or drafting for models other than Qwen3.8-27B.

## On Hugging Face, 13 November 2026

- Task: text generation
- Library: transformers
- Parameters: 1.9B
- Weights: about 3.8 GB in BF16; about 962 MB at 4-bit (estimate)
- Formats: Safetensors
- Downloads in the last 30 days: 429,580
- Likes: 301
- License: apache-2.0
- Based on: Qwen/Qwen3.8-27B
- Quantized versions: 20
- Fine-tunes: 3
- Tags: transformers, safetensors, qwen3, dflash2, speculative-decoding, block-diffusion, draft-model, sglang, vllm, text-generation

## Links

- Model: https://huggingface.co/incoai/Qwen3.8-27B-DFlash2
- Files: https://huggingface.co/incoai/Qwen3.8-27B-DFlash2/tree/main

## Get the model

Download its files with Hugging Face's command line:

```sh
pip install -U huggingface_hub
hf download incoai/Qwen3.8-27B-DFlash2
```

Then follow the usage in its model card. Nothing in this kit runs by itself.
````

## What is in it

1 files, 6 KB, downloaded as a zip.

```text
README.md  6 KB
```

## Source

[incoai/Qwen3.8-27B-DFlash2 on Hugging Face](https://huggingface.co/incoai/Qwen3.8-27B-DFlash2)

## 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 |
| --- | --- | --- | --- | --- | --- |
| Qwen3.8-27B-DFlash2 by incoai (this page) | 429,580 | 301 | 1.9B | apache-2.0 | 2026-09-17 |
| [Qwen3.8-27B-DFlash2](https://mindket.com/p/92c81d30-6c87-4d00-8e96-3e1241439f5d) | 46,660 | 335 | 1.9B | apache-2.0 | 2026-08-19 |
| [Qwen3.8-Flash-Next-DFlash2](https://mindket.com/p/395037c6-711b-471c-8552-e9f88ed25ab4) | 58,226 | 84 | 603M | apache-2.0 | 2026-10-19 |
| [Flint-DFlash2](https://mindket.com/p/097e9887-da16-4838-9d9a-ac148ae4398b) | 1,651 | 9 | 403M | apache-2.0 | 2026-10-26 |
| [Qwen3.8-Flash-Next-DFlash2-GGUF](https://mindket.com/p/f0d509d4-8e38-4f36-8052-59c52155132e) | 3,960 | 4 | 603M | apache-2.0 | 2026-10-31 |
| [Bielik-11B-v3.1-DFlash2](https://mindket.com/p/2711a318-550d-40de-b3db-4e250b26a909) | 44 | 3 | 1.2B | apache-2.0 | 2026-11-11 |

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: 2026-09-17
- First published: 2026-08-18
- Checked on Hugging Face: 2026-11-13
- Something wrong? Tell us: https://mindket.com/takedown#ask

## Get it

- [Open incoai/Qwen3.8-27B-DFlash2 on Hugging Face](https://huggingface.co/incoai/Qwen3.8-27B-DFlash2)
- [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/916f5a21-666c-4741-94ab-62684c958ac0)
- [Its page on Mindket](https://mindket.com/p/916f5a21-666c-4741-94ab-62684c958ac0)