- Size
- 2.0B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 27 Apr 2025the date the repo was created
- Context length
- 40k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen3-1.7B-BaseQwen3ForCausalLM
- On Hugging Face
- Qwen/Qwen3-1.7B2.7M downloads in the last 30 days, 631 likes
Scores
Epoch's name: qwen3-1.7b. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- effort none8.1%±2.828 Aug 2026, log
Epoch's name: qwen3-1.7b. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.88 GB, worked out from the model's config (Qwen/Qwen3-1.7B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
Qwen/Qwen3-1.7B-GGUF (the maker's own conversion), 187k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q8_0 | 1.7 GBfile size | 3.1 GB1.7 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen3-1.7B-GGUF:Q8_0Ollama ollama run hf.co/Qwen/Qwen3-1.7B-GGUF:Q8_0Download hf download Qwen/Qwen3-1.7B-GGUF --include "Qwen3-1.7B-Q8_0.gguf" --local-dir Qwen3-1.7B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 8bitlmstudio-community/Qwen3-1.7B-MLX-8bit | 1.7 GBfile size | 3.1 GB1.7 + 0.88 + 0.50 | Download page |
| MLX bf16Qwen/Qwen3-1.7B-MLX-bf16 | 3.2 GBfile size | 4.6 GB3.2 + 0.88 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 3.8 GBfile size | 5.2 GB3.8 + 0.88 + 0.50 |
hf download Qwen/Qwen3-1.7B --local-dir Qwen3-1.7BOther conversions (13; sizes not read)
- Qwen/Qwen3-1.7B-FP8 FP8, by the maker, 4.2k downloads
- Qwen/Qwen3-1.7B-GPTQ-Int8 GPTQ, int8, by the maker, 1.1k downloads
- unsloth/Qwen3-1.7B-unsloth-bnb-4bit bitsandbytes, 4bit, 49k downloads
- mobilint/Qwen3-1.7B Other, 28k downloads
- litert-community/Qwen3-1.7B Other, 20k downloads
- mlc-ai/Qwen3-1.7B-q4f16_1-MLC Other, 8.3k downloads
- unsloth/Qwen3-1.7B-bnb-4bit bitsandbytes, 4bit, 4.8k downloads
- onnx-community/Qwen3-1.7B-ONNX Other, 3.6k downloads
- RedHatAI/Qwen3-1.7B-FP8-dynamic FP8, 2.9k downloads
- Minguinho-zeze/Qwen3-1.7B-NVFP4A16-RTN NVFP4, 732 downloads
- Minguinho-zeze/Qwen3-1.7B-NVFP4-RTN-WikiText2 NVFP4, 673 downloads
- Orion-zhen/Qwen3-1.7B-AWQ AWQ, 631 downloads
- Minguinho-zeze/Qwen3-1.7B-NVFP4-RTN-Trace NVFP4, 550 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- lmstudio-community/Qwen3-1.7B-MLX-bf161.7B17kUnreviewed
- PerceptronAI/Isaac-0.12.6B5.0kUnreviewed
- tencent/Penguin-VL-2B2.2B619Unreviewed
- Cactus-Compute/Qwen3-1.7B32Unreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.