AI Index

Qwen3-1.7B

Language Alibaba Qwen Partly verified Released Apr 29, 2025
  • Reasoning
  • Reasoning can be off
  • Tool use
  • Structured output
  • Open weights

Prices

1 offering · prices as listed
Alibaba Cloud Model Studio Official Global · USD qwen3-1.7b
Conditions/ 1M tokensInputOutput
Standard no longer listed since Oct 1, 2026 past price, from the vendor’s page archived Jan 16, 2026$0.11$0.42

Prices from Alibaba Cloud Model Studio pricing (checked Sep 30, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Licence
apache-2.0
Family
qwen
Model ID

Not stated on Alibaba Qwen’s pages: max input, input modalities, output modalities, reasoning efforts, max thinking budget, built-in tools, knowledge cutoff, aliases.

Run locally

Weights: Qwen/Qwen3-1.7B
  • Parameters 2B
  • Dense
  • Native precision BF16
  • Layers 28
  • KV cache per token 112 KB
  • Config positions 40K (config.json max_position_embeddings)
  • API context 250K (maker’s API)
My hardware GeForce RTX 4090 24 GB · 1008 GB/s · 64 GB DDR5 dual channel · 89.6 GB/s
On your hardware · GeForce RTX 4090
Runs well BF16 (native) (automatic) 8K context 101–151 tok/sOne GPU
WeightsKV cacheOverheadUsable
Needs
≈ 5.2 GB (weights 3.8 (maker’s file) + KV cache 0.9 + overhead 0.5)
Usable
21.6 GB (90% of its memory)
Generation speed
101–151 tok/s
Longest context
40K (the model’s limit)
First token
about 0.07–0.10 s for a 2K prompt
PrecisionWeightsNeeds at 8KOn your hardwareLongest context
BF16 (native)maker’s file3.8 GB≈ 5.2Runs well 101–151 tok/s40K
Q8_0maker’s file1.7 GB≈ 3.1Runs well 182–273 tok/s40K
INT8 (GPTQ)maker’s file1.9 GB≈ 3.3Runs well 168–251 tok/s40K
FP8maker’s file2.5 GB≈ 3.8Runs well 140–210 tok/s40K
Q6_K1.6 GB≈ 2.9Runs well 193–290 tok/s40K
Q5_K_M1.3 GB≈ 2.7Runs well 211–317 tok/s40K
Q5_01.3 GB≈ 2.7Runs well 216–324 tok/s40K
Q4_K_M1.1 GB≈ 2.5Runs well 232–348 tok/s40K
Q4_01.1 GB≈ 2.4Runs well 242–363 tok/s40K
IQ4_XS1.0 GB≈ 2.4Runs well 250–374 tok/s40K
Q3_K_Mquality drops0.9 GB≈ 2.3Runs well 261–391 tok/s40K
IQ3_XXSquality drops0.7 GB≈ 2.1Runs well 294–440 tok/s40K
Q2_Kquality drops0.7 GB≈ 2.1Runs well 296–444 tok/s40K
IQ2_XXSquality drops0.5 GB≈ 1.9Runs well 345–517 tok/s40K

Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.

Compared with other hardware

Each at the highest precision it runs. Click one for details.

Smallest that runs it (Q4_K_M, 8K): GPU GeForce RTX 3080; unified memory Apple M5 · 16 GB.

Run commands

vLLM
vllm serve Qwen/Qwen3-1.7B --max-model-len 8192
Memory to fine-tune
Full≈ 32.3 GBDoesn’t fit your hardware
LoRA≈ 5.9 GBFits your hardware
QLoRA≈ 3.2 GBFits your hardware

Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.

Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated

Cited scores

From third-party leaderboards, not measured by us
  • Epoch AI · GPQA Diamond 38%

    #150 of 168 listed models · ±2.75

    Also listed: reasoning off 30.6%

  • Epoch AI · OTIS Mock AIME 2024–2025 8.1%

    #131 of 159 listed models · reasoning off · ±2.81

  • Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Nov 4, 2026
  • changes we made

Changes

All changes →

No changes recorded yet.

Sources

Alibaba Qwen’s official policies: data use, privacy, terms →

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

Alibaba Qwen · China · qwen.ai

Snapshots, the same family and other models from this provider