Benchmarks of SmolLM2 1.7B Instruct10
BenchmarkByScoreRank
No benchmark matches
—per task?
self-host onlyprice
—output speed?
8Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5 Minihighwins 84%—$0.053
OpenGemma 3 12Bunstatedwins 81%—$0.05 / $0.10Memory (4-bit): 0.9 GB → 6.1 GBBetterGPT-6 Lunamaxwins 85%—$0.068Function calling only with none · Chat Completions+3
BetterClaude Haiku 5.5highwins 86%—$0.079Remove sampling parameters+5BetterGPT-5.6 Lunaxhighwins 88%—$0.085ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 84%—$0.053GPT-6 Lunamaxwins 85%—$0.068Function calling only with none · Chat Completions+3Claude Haiku 5.5highwins 86%—$0.079Remove sampling parameters+5GPT-5.6 Lunaxhighwins 88%—$0.085GPT-5.6 Terraxhighwins 89%—$0.63Prompts with >272K input tokensModelScoreCostPer taskWhat changes
Gemma 3 12BunstatedOpenwins 81%—$0.05 / $0.10Memory (4-bit): 0.9 GB → 6.1 GB
Granite 4.2 8BunstatedOpenwins 80%—$0.06 / $0.25Memory (4-bit): 0.9 GB → 4.4 GBGranite 4.2 3BunstatedOpenwins 79%—$0.03 / $0.12Memory (4-bit): 0.9 GB → 1.8 GBGemma 3n E4B InstructunstatedOpenwins 79%——Memory (4-bit): 0.9 GB → 3.9 GBGranite 4.1 8BunstatedOpenwins 78%——Memory (4-bit): 0.9 GB → 4.4 GBRun it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
all categoriesChat & Knowledge
Arena Text · overall1,115#193
Arena Text · English1,092.6#202
Arena Text · instruction following1,029.1#202
Arena Text · non-English984.8#202
Arena Text · Russian981.1#201
Writing & Language
Arena Text · creative writing1,079#193
FAQ
How much does SmolLM2 1.7B Instruct cost?›
There is no per-unit API price: self-host only.
Is SmolLM2 1.7B Instruct free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is SmolLM2 1.7B Instruct, and what is it best at?›
#202 of 205 in Chat & Knowledge, #194 of 197 in Writing & Language.
Is SmolLM2 1.7B Instruct better than Llama 3.2 1B Instruct?›
On Arena Text · English, SmolLM2 1.7B Instruct scores 1,092.6 vs 1,116.6 — lower.
What is the context window of SmolLM2 1.7B Instruct?›
8K tokens.
When was SmolLM2 1.7B Instruct released? Is there a newer version?›
Released 2024-10-31. It is the current version in its line.
Is SmolLM2 1.7B Instruct open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run SmolLM2 1.7B Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can SmolLM2 1.7B Instruct read images?›
No, it accepts text only.
What is SmolLM2 1.7B Instruct?›
SmolLM2 1.7B Instruct is an open-weights language model from HuggingFaceTB, released Oct 2024.
What are the best alternatives to SmolLM2 1.7B Instruct?›
GPT-5 Mini (better), Gemma 3 12B (open weights).