Skip to content
Local AI Wizard
Your machine
Theme

Qwen3-235B-A22B-Thinking-2507

Qwen · Qwen/Qwen3-235B-A22B-Thinking-2507

Weights license: Apache 2.0 · code and components may use other terms

Reported by the publisher24 resultsQwen's model card · read 2026-10-25 · not ranked · see them
Memory needed~177 GBQ4 weights + working room, before the machine's reserve
Parameters235.1 BHub safetensors total
Repository updated2025-08-17A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

24 results · Qwen's model card · read 2026-10-25
MMLU-Pro
84.4Knowledge · thinking mode
MMLU-Redux
93.8Knowledge · thinking mode
GPQA
81.1Knowledge · thinking mode
SuperGPQA
64.9Knowledge · thinking mode
AIME25
92.3Reasoning · thinking mode
HMMT25
83.9Reasoning · thinking mode
LiveBench 20241125
78.4Reasoning · thinking mode
LiveCodeBench v6 (25.02-25.05)
74.1Coding · thinking mode
Every reported result24
CFEval
2,134Coding · thinking mode
OJBench
32.5Coding · thinking mode
IFEval
87.8Alignment · thinking mode
Arena-Hard v2$
79.7Alignment · thinking mode
Creative Writing v3
86.1Alignment · thinking mode
WritingBench
88.3Alignment · thinking mode
BFCL-v3
71.9Agent · thinking mode
TAU1-Retail
67.8Agent · thinking mode
TAU1-Airline
46.0Agent · thinking mode
TAU2-Retail
71.9Agent · thinking mode
TAU2-Airline
58.0Agent · thinking mode
TAU2-Telecom
45.6Agent · thinking mode
MultiIF
80.6Multilingualism · thinking mode
MMLU-ProX
81.0Multilingualism · thinking mode
INCLUDE
81.0Multilingualism · thinking mode
PolyMATH
60.1Multilingualism · thinking mode

Values as printed on the card, with the publisher's own settings (card section: Performance); column “Qwen3-235B-A22B-Thinking-2507”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
text-generation
Architecture
Qwen3MoeForCausalLM
Library in source
transformers
Weight license
Apache 2.0
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field12 fields
Revision checked
6cbffae6d8e28b986a6b17bd36f42f9fa0f1f0a5
Architecture
Qwen3MoeForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Tensor evidence
floating-tensor-elements · 235.09B · BF16checked 2026-09-26
Repository created
2025-07-25creation is not the model's release
Repository updated
2025-08-17a commit is not a release date
Hub downloads (30 days) · likes
13,427 · 418this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.