Qwen3.8-Flash-Next-FP8
Support summary
Qwen3.8-Flash-Next-FP8 is a checkpoint published by Qwen, built on the Qwen4ExpForConditionalGeneration architecture. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release.
- Documented hardware
- NVIDIA / CUDA and AMD / ROCm
- Documented quantization
- FP8
- Documented features
- Prefix caching, Reasoning parsers, Speculative decoding, Tensor parallelism, and Tool calling
- Configured context
- 262,144 tokens
- License
- qwen-community-1.0
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Qwen
- Task
- image text to text
- License
- qwen-community-1.0
- Library
- transformers
- Architecture
- Qwen4ExpForConditionalGeneration
- Weight tensor elements
- 180B
- Tensor types
- BF16, F8_E4M3, I64
- Quantization
- fp8
- Configured context
- 262,144 tokens
- Base models
- Qwen/Qwen3.8-Flash-Next
- Weight access
- Public
- Repository created
- 2026-08-24
Publisher deployment guidance
- vLLMVersion unspecified
The model card recommends current framework versions and links a deployment recipe; it does not pin a stable release.
Source: Qwen/Qwen3.8-Flash-Next-FP8 · publisher model cardReviewed - SGLangVersion unspecified
The model card recommends current framework versions and links a deployment recipe; it does not pin a stable release.
Source: Qwen/Qwen3.8-Flash-Next-FP8 · publisher model cardReviewed
Model notes and sources
- Qwen/Qwen3.8-Flash-Next-FP8 · publisher model card
- Qwen/Qwen3.8-Flash-Next-FP8 · Hugging Face metadata
- Qwen/Qwen3.8-Flash-Next-FP8 · publisher configuration
- vllm · models/Qwen/Qwen3.8-Flash-Next.yaml
- sglang · docs/src/snippets/configs/Qwen/qwen3.8-flash-next.jsx
- sglang · docs/cookbook/autoregressive/Qwen/Qwen3.8-Flash-Next.mdx
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/Qwen/Qwen3.8-Flash-Next.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/Qwen/Qwen3.8-Flash-Next.mdxSource 2: sglang · docs/src/snippets/_deployment.jsxSource 3: sglang · docs/src/snippets/configs/Qwen/qwen3.8-flash-next.jsxSource 4: sglang · docs/src/snippets/configs/Qwen/qwen3.8-flash-next-benchmarks.jsxSource 5: sglang · docs/src/snippets/_playground.jsxReviewed | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||