Qwen3 1.7B
Qwen3 1.7BRankingin non-thinking mode?
Alternatives?
CheaperCommand A+thinkingOpen×6.9-6%$0.30 / $1.50Memory (4-bit): 1 GB → 131 GB
BetterGPT-6 Lunalow+16%-69%$0.005Function calling only with none · Chat Completions+3OOpenMiniCPM5 1Bnon-thinking×108.5——
CheaperMiniMax M3thinkingOpen×5.3-18%$0.51Memory (4-bit): 1 GB → 256 GB+2
CheaperLing 3.0 Flash VLthinkingOpen×4.4-86%$0.06 / $0.18Memory (4-bit): 1 GB → 75 GBCommand A+thinkingOpen×6.9-6%$0.30 / $1.50Memory (4-bit): 1 GB → 131 GBMiniMax M3thinkingOpen×5.3-18%$0.51Memory (4-bit): 1 GB → 256 GB+2Ling 3.0 Flash VLthinkingOpen×4.4-86%$0.06 / $0.18Memory (4-bit): 1 GB → 75 GB
Solar Pro 4thinking×4.1-18%$0.71
MiMo v2.5 ProthinkingOpen×4-15%$0.054Memory (4-bit): 1 GB → 614 GBGPT-6 Lunalow+16%-69%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen×3.7-92%$0.006Memory (4-bit): 1 GB → 1.8 GB
Ministral 3 3B 2512Open+22%-84%$0.008Memory (4-bit): 1 GB → 1.9 GB
Gemma 4 E4BthinkingOpen×3.2-94%$0.008Memory (4-bit): 1 GB → 4 GBGPT-5.6 Lunalow+9%-30%$0.01Granite 4.2 3BthinkingOpen×3.7-92%$0.006Memory (4-bit): 1 GB → 1.8 GBQwen3 VL 4B Instructnon-thinkingOpensame—$0.10 / $0.60Memory (4-bit): 1 GB → 2.2 GBQwen3 8Bnon-thinkingOpen+2%—$0.18 / $0.70Memory (4-bit): 1 GB → 4.1 GBQwen3 30B A3B Instruct 2507non-thinkingOpen+2%—$0.09 / $0.30Memory (4-bit): 1 GB → 18 GBQwen3 Max Thinkingthinking+3%—$1.20 / $6Qwen3 0.6Bnon-thinkingOpen+4%—$0.04 / $0.08Qwen3 Coder Nextnon-thinkingOpen+4%—$0.47Memory (4-bit): 1 GB → 48 GBQwen3 VL 30B A3B Instructnon-thinkingOpen+4%—$0.15 / $0.50Memory (4-bit): 1 GB → 19 GBQwen3 Next 80B A3B Instructnon-thinkingOpen+5%—$0.50 / $2Memory (4-bit): 1 GB → 49 GBAll Alibaba (Qwen) models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Qwen3 1.7B cost?›
$0.32 per 1M input tokens and $1.60 per 1M output tokens (cheapest host: Featherless).
Is Qwen3 1.7B free to use?›
There is no free API; the cheapest paid price is $0.32 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Qwen3 1.7B, and what is it best at?›
#264 of 334 in Chat & Knowledge, #210 of 239 in Coding, #183 of 242 in Agents & Tool Use, #238 of 245 in Writing & Language.
Is Qwen3 1.7B better than Ling 1T?›
On AA Omniscience · Hallucination Rate, Qwen3 1.7B scores 94.8 vs 94.7 — about the same.
How can I use Qwen3 1.7B?›
Through the API of Featherless.
What is the context window of Qwen3 1.7B?›
33K tokens.
When was Qwen3 1.7B released? Is there a newer version?›
Released 2025-04-28. It has been superseded by Qwen3.5 2B.
Is Qwen3 1.7B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen3 1.7B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qwen3 1.7B read images?›
No, it accepts text only.
What is Qwen3 1.7B?›
Qwen3 1.7B is an open-weights language model from Alibaba (Qwen), released Apr 2025.
What are the best alternatives to Qwen3 1.7B?›
Command A+ (cheaper), GPT-6 Luna (better), MiniCPM5 1B (open weights).