Model AtlasA selection map of agent foundation models 中文
Start researchModelsPapersGuideCompare 中文

Search the atlas

Esc to close · Cmd/Ctrl + K to open
Alibaba

Qwen3-1.7B

Reasoning · 2025-04-29 · Verified
Research summary

Research summary

Good for
Inference, SFT, RL
Not suitable / limits
No explicit limitation evidence
How to get it
Open weights
Hardware tier
Inference: 16GB GPU · LoRA: Not reported
Paper adoption
1 · Paper adoption
Reproduction risk
Some key facts need verification
Evidence state
Verified · Some key facts need verification
Model positioningReasoningTool useAgentMultilingual

Access and distribution ladder

ProductPending verificationPending verification
APIPending verificationNot applicable
WeightsYesYes
BaseYesYes
Finetuning allowedYesYes
Derivative distributionYesYes

At a glance

Model positioning
Reasoning, Tool use, Agent, Multilingual
Architecture
Dense
Parameters
1.7B parameters
Active parameters
1.7B
Experts
Not applicable
Experts / token
Not applicable
Context length
32768 tokens
Modalities
Text
Base checkpoint
Yes
Finetuning allowed
Yes
License
Apache-2.0

Unresolved fields

These fields stay explicit instead of being guessed; verify them against the source or model card.

7 key fields need verification

How to read unknown states

These states intentionally preserve evidence boundaries; they are not false, zero, or definite facts.

Not disclosedThe official source does not disclose this; do not infer that it is absent.
The official source does not disclose this; do not infer that it is absent.
Not applicableThis field does not apply to this record; it is not missing or negative.
This field does not apply to this record; it is not missing or negative.
Not reportedThe source or paper did not report it; this is not false, zero, or confirmed absence.
The source or paper did not report it; this is not false, zero, or confirmed absence.
Not verifiedThe field is retained, but current evidence is not verified; add first-party evidence before relying on it.
The field is retained, but current evidence is not verified; add first-party evidence before relying on it.
Conflicting evidenceFirst-party sources conflict; no single value is selected.
First-party sources conflict; no single value is selected.
Not publishedThe record is not published yet; this is not the same as a broken source link.
The record is not published yet; this is not the same as a broken source link.
UnavailableThe current source is unavailable; do not infer that the fact does not exist.
The current source is unavailable; do not infer that the fact does not exist.

Access & distribution

Weights status
Released
Full weights date
2025-04-29
API status
Not applicable
Product status
Pending verification
Openness classification
Open weight
Custom license
No
Derivative distribution
Allowed
Commercial use
Allowed
Model revision
Pin the model revision
Preserve reasoning history
Not verified

Specializations & research readiness

ReasoningTool useAgentMultilingual
Inference
Yes
LoRA
Not reported
SFT
Yes
RL
Yes
Transformers
Yes
vLLM
Yes
SGLang
Yes
veRL recipe
Yes

Hardware tiers

Inference
16GB GPU
LoRA
Not reported
Full-parameter SFT
Not reported
RL
Multi-GPU

Paper adoption

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Actor · weights updated

2026-07-16

Replacement candidates and family versions

Candidates are derived from catalog family, generation, and release metadata; this is not a quality score or a substitute for experiments.