This repository contains the DFlash 2 draft model for `Qwen/Qwen3.8-Flash-Next`. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. 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. Serve with SGLang. Flash-Next needs a small target-feature capture patch, included in this repository and validated at TP1, until support lands upstream:
Explore AI models 84999
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Caelistus-Gladius-Excalibur-RP-2.6B-Thinking-v0.1
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Erebus-RP-12B-Instruct-2608-v1-GGUF
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Erebus-RP-Mini-4B-Instruct-2608-v0.1
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
gemma-3-4b-it-roleplay-tuned-v1
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
gemma-3-4b-it-roleplay-tuned-v2
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
LFM-2.5-1.2b-Instruct-roleplay-tuned
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Llama-3.2-3B-Instruct-roleplay-tuned
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Ministral-3-3B-Instruct-2512-roleplay-tuned-ERP-tolerant
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Nyx-RP-9B-Instruct-2608-v1
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Nyx-RP-Mini-2.6B-Instruct-2608-v0.1-GGUF
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Palette-RP-4B-2609-v0.1
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Palette-RP-9B-2609-v0.05
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Palette-RP-9B-2609-v0.1
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Pallete-2.6B-RP-Reasoning-2609-v1a
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Qwen-3.5-2b-roleplay-tuned
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Super-Slop-Machina-Roleplay-1.2b
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Super-Slop-Machina-Roleplay-1.2b-V4-ERP-Tolerant-it
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Super-Slop-Machina-Roleplay-1.2b-V4-ERP-Tolerant-Preview
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Super-Slop-Machina-RP-XXL-Small-3B-2608
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Super-Slop-Machina-XXL-v0.1-4B
Indexnusrefather基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Index-1.9B-Character-GGUF
IndexTeam基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.