Model reference · open weights

Qwen3.8-DFlash2

Qwen3.8-DFlash2 is an open-weight language model from z-lab, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

LLMs z-lab 1 variants 142k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Qwen3.8-DFlash2 is

Qwen3.8-27B-DFlash2 Blog | GitHub This repository contains the DFlash 2 draft model for Qwen/Qwen3.8-27B. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. This repository is a mirror of incoai/Qwen3.8-27B-DFlash2. DFlash 2 is a block-diffusion drafter for speculative decoding. It predicts a whole block of tokens in a single pass and keeps the top candidates at every position. A lightweight selector then traces one coherent path through them. Two-tap dynamic convolutions in the backbone keep the draft from decaying toward the end of the block. Decoding is lossless: greedy output matches the target model exactly, and sampling preserves its distribution. Quick Start Serve with SGLang: Or with vLLM: See the blog post for other engines and more details. Evaluation - Runtime: SGLang on one NVIDIA H200, with FlashAttention 3 for target and draft attention - Speculation block size: 8 (7 draft tokens per verification step) - Sampling: Qwen3.8's officially recommended parameters (temperature 1.0, top-p 0.95, top-k 20), with xhigh reasoning effort - Maximum new tokens: 4096 - Prompts: benchmark formatting from z-lab/dflash We compare autoregressive decoding, Qwen3.8's built-in seven-token MTP, a community DSpark drafter (RadixArk/Qwen3.8-27B-DSpark), and DFlash 2. All speculative methods propose seven draft tokens per verification step. Acceptance Length Acceptance length is the per-request mean of completion tokens divided by verification steps. Higher is better. Throughput Throughput is total output tokens divided by end-to-end wall time. Each cell shows output tok/s (speedup vs. autoregressive). Concurrency 1 Concurrency 8 Concurrency 32 Citation If you find DFlash 2 useful, please cite: Please also cite the original DFlash paper:

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerz-lab
TypeLanguage models
Parameters (lead)1.9B
Context256k tokens
Variants1
Runs withtransformers
Based onQwen/Qwen3.8-27B
Released2026-08-15
Popularity142k downloads / month
Likes255
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Qwen3.8-27B-DFlash21.9BBF16~4.4 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys z-lab-qwen3-8-dflash2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (z-lab-qwen3-8-dflash2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"z-lab-qwen3-8-dflash2","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Tags

transformers safetensors qwen3 dflash2 speculative-decoding block-diffusion draft-model sglang vllm text-generation text-generation-inference

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Qwen3.8-DFlash2 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms