Qwen3 14B
alibaba/qwen3-14b- Alibaba
- Family · Qwen3
- Released 28 Apr 2025
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context40K
Max output16K
Input / 1M$0.12
Output / 1M$0.242× input
Scores · standing
Intelligence6.7#365/490
Coding13.8#163/196
Usage
Tokens / day376.7M▼ 14% 7d
Usage rank#240
Requests / day171.5K
Tool calls / req0.04
Per request · 30 days
Avg input1.7K0.1× median
Avg output5430.8× median
Reasoning share67%1.2× median
Tool-call failures1%0.5× median
Consumption
Peak 2.3B 5 OctLow 183.4M 19 OctRank today #240
News & trends
3 mentions this week ▲ 200%this model · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 family
- Qwen3.8 27b (Q6) casually breaking reCAPTCHA838 upvotes
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard416 points
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted edits26 points
- New Card for Qwen3.8 27b and MiniMax H3656 upvotes
- Qwen 3.8 27B vs Strata Coder - Local LLM battle75.2K views
- DavidAU Qwen3.8 27B Turbo Brilliance 50X-Reasoning... tested - Local LLM setup87.7K views
News · latest from Qwen3
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
- How to train your own Jev for $17Together AI · 23 Sep
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 2 providers, latest day
Output speed#227/33448 tok/s1.3× slower than median
Fastest provider56 tok/sbest of 2 providers
First token#1681.08 sabout median
#7 cheapest of 37 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases33.7
Technical details
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-03-31
- License
- Apache 2.0
- Parameters
- 14.8B
- Moderation
- none
- Downloads · likes
- 13.0M · 531
Request parameters 19
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+9 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Low-cost bulk classification and extraction
- Self-hosted assistants on modest hardware
- Math and reasoning at small scale
- Structured JSON output with tool calling
Think twice for
- Very long documents
- Image understanding
- Frontier-level coding agents
- Hardest scientific reasoning
Research papers
- Can Personal Requirements Become Supervision for Planning?29 Oct
- Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels27 Oct
- Self-Evolving Agents through Privileged Retrospective Distillation20 Oct
- Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents8 Oct
- SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference8 Oct
- The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning6 Oct
- AVSD-Scenes: A Dataset for Audio-Visual Description of Urban Scenes1 Oct
- MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller29 Sep
Same family
Qwen3- 7.2
- 6.0
- 6.9
- 6.1
- 5.2
- 13.1
Alternatives
other vendors · similar capability- 8.5
- 11.6
- 6.7
- 9.7
Want Qwen3 14B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.