Qwen3.8-2.4T-A95B

CheckpointQwen/Qwen3.8-2.4T-A95BModel card indexedModel card

Support summary

Qwen3.8-2.4T-A95B is a checkpoint published by Qwen, built on the Qwen3_5MoeForCausalLM architecture. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release.

Documented hardware
NVIDIA / CUDA
Documented quantization
BF16
Documented features
Reasoning parsers, Speculative decoding, Tensor parallelism, and Tool calling
Configured context
262,144 tokens
License
qwen3.8-max

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
text generation
Library
transformers
Architecture
Qwen3_5MoeForCausalLM
Weight tensor elements
2.4T
Tensor types
BF16
Configured context
262,144 tokens
Weight access
Public
Repository created
2026-08-08
Source 1: Qwen/Qwen3.8-2.4T-A95B · publisher model cardSource 2: Qwen/Qwen3.8-2.4T-A95B · Hugging Face metadataSource 3: Qwen/Qwen3.8-2.4T-A95B · publisher configurationReviewed

Publisher deployment guidance

Model notes and sources

Engine support

3 engines

Engine support for Qwen3.8-2.4T-A95B
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLMVersion not pinnedRecipe / cookbookDocumented recipe

Official recipe

Source: vllm · models/Qwen/Qwen3.8-2.4T-A95B.yamlReviewed
No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLangVersion not pinnedRecipe / cookbookDocumented recipe

Official recipe

Source 1: sglang · docs/cookbook/autoregressive/Qwen/Qwen3.8.mdxSource 2: sglang · docs/src/snippets/_deployment.jsxSource 3: sglang · docs/src/snippets/configs/Qwen/qwen3.8.jsxSource 4: sglang · docs/src/snippets/configs/Qwen/qwen3.8-benchmarks.jsxSource 5: sglang · docs/src/snippets/_playground.jsxReviewed
No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks