Skip to content
Local AI Wizard
Your machine
Theme

Qwen3-4B-Thinking-2507

Qwen · Qwen/Qwen3-4B-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~3 GBQ4 weights + working room, before the machine's reserve
Parameters4 BHub safetensors total
Repository updated2025-08-06A 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
74.0Knowledge · thinking mode
MMLU-Redux
86.1Knowledge · thinking mode
GPQA
65.8Knowledge · thinking mode
SuperGPQA
47.8Knowledge · thinking mode
AIME25
81.3Reasoning · thinking mode
HMMT25
55.5Reasoning · thinking mode
LiveBench 20241125
71.8Reasoning · thinking mode
LiveCodeBench v6 (25.02-25.05)
55.2Coding · thinking mode
Every reported result24
CFEval
1,852Coding · thinking mode
OJBench
17.9Coding · thinking mode
IFEval
87.4Alignment · thinking mode
Arena-Hard v2$
34.9Alignment · thinking mode
Creative Writing v3
75.6Alignment · thinking mode
WritingBench
83.3Alignment · thinking mode
BFCL-v3
71.2Agent · thinking mode
TAU1-Retail
66.1Agent · thinking mode
TAU1-Airline
48.0Agent · thinking mode
TAU2-Retail
53.5Agent · thinking mode
TAU2-Airline
58.0Agent · thinking mode
TAU2-Telecom
27.2Agent · thinking mode
MultiIF
77.3Multilingualism · thinking mode
MMLU-ProX
64.2Multilingualism · thinking mode
INCLUDE
64.4Multilingualism · thinking mode
PolyMATH
46.2Multilingualism · thinking mode

Values as printed on the card, with the publisher's own settings (card section: Performance); column “Qwen3-4B-Thinking-2507”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 118

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 118

Within memory, outside the fast part 1

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

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.

Checkpoint / source
Qwen/Qwen3-4B-Thinking-2507
Task
text-generation
Architecture
Qwen3ForCausalLM
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
768f209d9ea81521153ed38c47d515654e938aea
Architecture
Qwen3ForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Tensor evidence
floating-tensor-elements · 4.02B · BF16checked 2026-09-26
Repository created
2025-08-05creation is not the model's release
Repository updated
2025-08-06a commit is not a release date
Hub downloads (30 days) · likes
646,075 · 628this 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.