Qwen3 14B
AlibabaReleased Apr 28, 2025Open weights · Apache 2.0qwen3-14b
- Intelligence (Epoch)
- 138 · 86th of 111
- Reasoning
- yes
- Knowledge cutoff
- September 2025
- Context
- 41K tokens
- Max output
- 16k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
- Alibaba's API
- yes
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Alibaba · cutoff: aiknowledgecutoff.com
The cheapest host, NextBit, serves int4 weights (maker: bf16). Weights and context per host
Intelligence for the price
7 models score higher for the same price or less; it ranks 8 of the 17 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 138 with an interval of 133 to 140.
Against its rivals
The best of its price range and the top score
- Qwen3 14Bthis model$0.32138
- Claude Opus 5.5top score$24.00169
- Claude Haiku 5.5same price range$0.60159
- GPT-6 Lunasame price range$0.60157
Same level for 2.7× less: gpt-oss-20b at AkashML, $0.12 per M input + output · their Epoch intervals overlap (138 against 138).
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
Run it yourself
open weights, Apache 2.0 · fits 6 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 14B
- dense
- Memory needed
- 8 GB
- in INT4 · 17 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.17/h, about $124 a month
- Worth it above
- 388M tokens
- a month, against the cheapest API at $0.32 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 8 GB | RTX 3090 · $0.17/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 17 GB | RTX 3090 · $0.17/h | near-lossless |
| FP16 (full) | 34 GB | A100 · $1.19/h | reference quality |
At home: in INT4 it fits a RTX 5090 (32 GB) + host PC (plus a host PC), about $3,500 once, or $0.1332/h over 3 years, electricity aside; it pays for itself after about 11B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| NextBitint4 (bf16) · 40K ctx | $0.10 | $0.22 | — | 59 | 1.41 s | 99.7% | Oct 23 |
| DeepInfrafp8 (bf16) · 40K ctx · 16K out | $0.12 | $0.24 | — | 64 | 0.41 s | 100% | Oct 23 |
| Alibabaprecision not read: host terms · 8K out | $0.35 | $1.40 | — | — | — | — | Oct 23 |
3 of 3 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| NextBit | int4 | 40K | not read: host terms | no | yes | yes |
| DeepInfra | fp8 | 40K | 16K | yes | yes | yes |
| Alibaba | not read: host terms | not read: host terms | 8K | — | — | — |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Qwen3 14B spec sheet, field by field, with sources
Qwen3 14B spec sheetmaker-declared
What Alibaba declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 40,960 tokens
- Parameters
- 14,768,307,200≈ 14.8B
- Active experts
- none declared in the weights
- Weight precision
- bfloat16
- License
- Apache 2.0 — open weights, permissivecurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ September 2025 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ April 28, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- Qwen3ForCausalLM
- Layers
- 40
- Vocabulary
- 151,936 tokens
- Weights first published
- April 27, 2025
- Weights last updated
- July 26, 2025
- Papers
- arXiv:2309.00071 · arXiv:2505.09388
Qwen/Qwen3-14B · config.json @ 40c0698 · read 2026-10-08 · 5 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| NextBit | $0.21 | $0.91 | $0.62 |
| DeepInfra | $0.24 | $1.08 | $0.72 |
| Alibaba | $1.05 | $3.50 | $2.80 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Alibaba models · all its models, hosts and history ›
- Qwen3.8 27B16 providers · from $1.29
- Qwen3.6 35B A3B12 providers · from $1.00
- Qwen3 235B A22B Instruct 250710 providers · from $0.44
- Qwen3.5 397B A17B10 providers · from $3.45
- Qwen3.6 27B9 providers · from $2.25
- Qwen3.5-35B-A3B8 providers · from $1.14