- Size
- 494M 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
- 16 Sep 2024the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen2.5-0.5BQwen2ForCausalLM
- On Hugging Face
- Qwen/Qwen2.5-0.5B-Instruct4.1M downloads in the last 30 days, 754 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: 0.09 GB, worked out from the model's config (Qwen/Qwen2.5-0.5B-Instruct), 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/Qwen2.5-0.5B-Instruct-GGUF (the maker's own conversion), 490k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 0.39 GBfile size | 0.98 GB0.39 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q2_KOllama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q2_KDownload hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q2_k.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_0 | 0.40 GBfile size | 0.99 GB0.40 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q4_0Ollama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q4_0Download hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q4_0.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q3_K_M | 0.40 GBfile size | 1.00 GB0.40 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_MOllama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_MDownload hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q3_k_m.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q5_0 | 0.46 GBfile size | 1.1 GB0.46 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q5_0Ollama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q5_0Download hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q5_0.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_K_M | 0.46 GBfile size | 1.1 GB0.46 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_MDownload hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q4_k_m.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q5_K_M | 0.49 GBfile size | 1.1 GB0.49 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q5_K_MOllama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q5_K_MDownload hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q5_k_m.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q6_K | 0.61 GBfile size | 1.2 GB0.61 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q6_KOllama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q6_KDownload hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q6_k.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q8_0 | 0.63 GBfile size | 1.2 GB0.63 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q8_0Ollama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q8_0Download hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-q8_0.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| F16 | 1.2 GBfile size | 1.8 GB1.2 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen2.5-0.5B-Instruct-GGUF:F16Ollama ollama run hf.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF:F16Download hf download Qwen/Qwen2.5-0.5B-Instruct-GGUF --include "qwen2.5-0.5b-instruct-fp16.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitlmstudio-community/Qwen2.5-0.5B-Instruct-MLX-4bit | 0.26 GBfile size | 0.85 GB0.26 + 0.09 + 0.50 | Download page |
| MLX 8bitlmstudio-community/Qwen2.5-0.5B-Instruct-MLX-8bit | 0.49 GBfile size | 1.1 GB0.49 + 0.09 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 0.92 GBfile size | 1.5 GB0.92 + 0.09 + 0.50 |
hf download Qwen/Qwen2.5-0.5B-Instruct --local-dir Qwen2.5-0.5B-InstructOther conversions (9; sizes not read)
- Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4 GPTQ, int4, by the maker, 3.0k downloads
- Qwen/Qwen2.5-0.5B-Instruct-AWQ AWQ, by the maker, 2.5k downloads
- Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8 GPTQ, int8, by the maker, 1.3k downloads
- mlc-ai/Qwen2.5-0.5B-Instruct-q4f16_1-MLC Other, 72k downloads
- onnx-community/Qwen2.5-0.5B-Instruct Other, 58k downloads
- unsloth/Qwen2.5-0.5B-Instruct-unsloth-bnb-4bit bitsandbytes, 4bit, 35k downloads
- mobilint/Qwen2.5-0.5B-Instruct Other, 28k downloads
- unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit bitsandbytes, 4bit, 15k downloads
- mlc-ai/Qwen2.5-0.5B-Instruct-q4f32_1-MLC Other, 4.7k 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.
- unsloth/Qwen2.5-0.5B-Instruct494M22kUnreviewed
- litert-community/Qwen2.5-0.5B-Instruct13kUnreviewed
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.