Qwen3.5-122B-A10B-GPTQ-Int4

CheckpointQwen/Qwen3.5-122B-A10B-GPTQ-Int4Model card indexedModel card

Support summary

Qwen3.5-122B-A10B-GPTQ-Int4 is a checkpoint published by Qwen, built on the Qwen3_5MoeForConditionalGeneration architecture. Official recipes or cookbooks cover vLLM, without pinning a stable release.

Documented quantization: int4
Configured context: 262,144 tokens
License: apache-2.0

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: apache-2.0
Library: transformers
Architecture: Qwen3_5MoeForConditionalGeneration
Weight tensor elements: 125.1B
Tensor types: BF16, F32, I32
Quantization: gptq
Configured context: 262,144 tokens
Weight access: Public
Repository created: 2026-03-03

Source 1 Source 2 Source 3Reviewed 2026-09-05

Model notes and sources

Engine support

3 engines

Engine support for Qwen3.5-122B-A10B-GPTQ-Int4
Engine	Release	Evidence scope	Last known supported
vLLM	Version not pinnedRecipe / cookbook	Documented recipe Official recipe Source: vllm · models/Qwen/Qwen3.5-122B-A10B.yamlReviewed 2026-09-05	No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang	`0.5.19`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM	`1.2.1`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks

vLLM · Qwen3.5-122B-A10B