- Size
- 1.7B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 28 Apr 2025the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen3ForCausalLM
- On Hugging Face
- Qwen/Qwen3-1.7B-Base636k downloads in the last 30 days, 102 likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
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.
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-Base), 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
mradermacher/Qwen3-1.7B-Base-i1-GGUF (converted by mradermacher), 936 downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 0.70 GBfile size | 2.1 GB0.70 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_XXSOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_XXSDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-IQ3_XXS.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| IQ3_XS | 0.78 GBfile size | 2.2 GB0.78 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_XSOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_XSDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-IQ3_XS.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| IQ3_S | 0.81 GBfile size | 2.2 GB0.81 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_SOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_SDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-IQ3_S.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q3_K_S | 0.81 GBfile size | 2.2 GB0.81 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q3_K_SOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q3_K_SDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q3_K_S.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| IQ3_M | 0.83 GBfile size | 2.2 GB0.83 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_MOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ3_MDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-IQ3_M.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q3_K_M | 0.88 GBfile size | 2.3 GB0.88 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q3_K_MOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q3_K_MDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q3_K_M.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q3_K_L | 0.93 GBfile size | 2.3 GB0.93 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q3_K_LOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q3_K_LDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q3_K_L.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| IQ4_XS | 0.94 GBfile size | 2.3 GB0.94 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ4_XSOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ4_XSDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-IQ4_XS.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| IQ4_NL | 0.98 GBfile size | 2.4 GB0.98 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ4_NLOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:IQ4_NLDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-IQ4_NL.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q4_0 | 0.98 GBfile size | 2.4 GB0.98 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_0Ollama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_0Download hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q4_0.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q4_K_S | 0.99 GBfile size | 2.4 GB0.99 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_K_SOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_K_SDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q4_K_S.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q4_K_M | 1.0 GBfile size | 2.4 GB1.0 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_K_MOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_K_MDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q4_K_M.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q4_1 | 1.1 GBfile size | 2.4 GB1.1 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_1Ollama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q4_1Download hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q4_1.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q5_K_S | 1.1 GBfile size | 2.5 GB1.1 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q5_K_SOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q5_K_SDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q5_K_S.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q5_K_M | 1.2 GBfile size | 2.5 GB1.2 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q5_K_MOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q5_K_MDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q5_K_M.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
| Q6_K | 1.3 GBfile size | 2.7 GB1.3 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q6_KOllama ollama run hf.co/mradermacher/Qwen3-1.7B-Base-i1-GGUF:Q6_KDownload hf download mradermacher/Qwen3-1.7B-Base-i1-GGUF --include "Qwen3-1.7B-Base.i1-Q6_K.gguf" --local-dir Qwen3-1.7B-Base-i1-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitbluevisor/Qwen3-1.7B-Base-4bit-mlx | 0.90 GBfile size | 2.3 GB0.90 + 0.88 + 0.50 | Download page |
| MLX 4bitjohnlakness/Qwen3-1.7B-Base-mlx-4Bit | 0.90 GBfile size | 2.3 GB0.90 + 0.88 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 3.2 GBfile size | 4.6 GB3.2 + 0.88 + 0.50 |
hf download Qwen/Qwen3-1.7B-Base --local-dir Qwen3-1.7B-BaseOther conversions (10; sizes not read)
- unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit bitsandbytes, 4bit, 4.2k downloads
- unsloth/Qwen3-1.7B-Base-bnb-4bit bitsandbytes, 4bit, 1.3k downloads
- Arm/qwen3-1-7b-base-q4-k-m-llamacpp-vivo-x300 GGUF, 406 downloads
- ThakiCloud/Qwen3-1.7B-Base-CareQ-2.4bpw Other, 363 downloads
- liodon-ai/Qwen3-1.7B-Base-FP8 FP8, 50 downloads
- Arm/qwen3-1-7b-base-onnx-genai-int4-kquantlast-vivo-x300 GPTQ, int4, 48 downloads
- mp3pintyo/unsloth_Qwen3-1.7B-Base-v2 bitsandbytes, 45 downloads
- isogen/Qwen3-1.7B-Base-exl3-8bpw-h8 EXL3, 12 downloads
- liodon-ai/Qwen3-1.7B-Base-ONNX Other, 6 downloads
- mistralrs-community/Qwen3-1.7B-Base-UQFF Other, 4 downloads
The Hub tags 58 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.
- Qwen/Qwen3-1.7B2.0B2.7MReviewed
- PrimeIntellect/Qwen3-1.7B2.0B245kUnreviewed
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.