- 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
- 15 Sep 2024the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen2ForCausalLM
- On Hugging Face
- Qwen/Qwen2.5-0.5B1.2M downloads in the last 30 days, 496 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), 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
ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF (converted by ThomasBaruzier), 8.5k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 0.31 GBfile size | 0.90 GB0.31 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_XXSOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_XXSDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-IQ3_XXS.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q3_K_S | 0.32 GBfile size | 0.91 GB0.32 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_SOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_SDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q3_K_S.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| IQ3_S | 0.32 GBfile size | 0.91 GB0.32 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_SOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_SDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-IQ3_S.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| IQ3_XS | 0.32 GBfile size | 0.91 GB0.32 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_XSOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_XSDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-IQ3_XS.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| IQ3_M | 0.32 GBfile size | 0.91 GB0.32 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_MOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ3_MDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-IQ3_M.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| IQ4_XS | 0.33 GBfile size | 0.92 GB0.33 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ4_XSOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ4_XSDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-IQ4_XS.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_0_4_4 | 0.33 GBfile size | 0.92 GB0.33 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0_4_4Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0_4_4Download hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q4_0_4_4.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_0_4_8 | 0.33 GBfile size | 0.92 GB0.33 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0_4_8Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0_4_8Download hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q4_0_4_8.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_0_8_8 | 0.33 GBfile size | 0.92 GB0.33 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0_8_8Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0_8_8Download hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q4_0_8_8.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| IQ4_NL | 0.33 GBfile size | 0.92 GB0.33 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ4_NLOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:IQ4_NLDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-IQ4_NL.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_0 | 0.33 GBfile size | 0.92 GB0.33 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_0Download hf download ThomasBaruzier/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 | 0.33 GBfile size | 0.92 GB0.33 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_MOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_MDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q3_K_M.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q3_K_L | 0.34 GBfile size | 0.94 GB0.34 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_LOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q3_K_LDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q3_K_L.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_1 | 0.35 GBfile size | 0.94 GB0.35 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_1Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_1Download hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q4_1.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q4_K_S | 0.36 GBfile size | 0.95 GB0.36 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_SOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_SDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q4_K_S.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q5_0 | 0.37 GBfile size | 0.96 GB0.37 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_0Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_0Download hf download ThomasBaruzier/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 | 0.37 GBfile size | 0.96 GB0.37 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_MDownload hf download ThomasBaruzier/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_S | 0.38 GBfile size | 0.98 GB0.38 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_K_SOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_K_SDownload hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q5_K_S.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q5_1 | 0.39 GBfile size | 0.98 GB0.39 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_1Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_1Download hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q5_1.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| Q5_K_M | 0.39 GBfile size | 0.98 GB0.39 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_K_MOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q5_K_MDownload hf download ThomasBaruzier/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 | 0.47 GBfile size | 1.1 GB0.47 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q6_KOllama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q6_KDownload hf download ThomasBaruzier/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 | 0.49 GBfile size | 1.1 GB0.49 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q8_0Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:Q8_0Download hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-Q8_0.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
| F16 | 0.93 GBfile size | 1.5 GB0.93 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:F16Ollama ollama run hf.co/ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF:F16Download hf download ThomasBaruzier/Qwen2.5-0.5B-Instruct-GGUF --include "Qwen2.5-0.5B-Instruct-F16.gguf" --local-dir Qwen2.5-0.5B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitharishforaiandml/Qwen2.5-0.5B-mlx-4Bit | 0.26 GBfile size | 0.85 GB0.26 + 0.09 + 0.50 | Download page |
| MLXekovshilovsky/Qwen2.5-0.5B-TQ8-TP2 | 0.57 GBfile size | 1.2 GB0.57 + 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 --local-dir Qwen2.5-0.5BOther conversions (14; sizes not read)
- unsloth/Qwen2.5-0.5B-unsloth-bnb-4bit bitsandbytes, 4bit, 4.5k downloads
- onnx-community/Qwen2.5-0.5B Other, 1.2k downloads
- unsloth/Qwen2.5-0.5B-bnb-4bit bitsandbytes, 4bit, 966 downloads
- RedHatAI/Qwen2.5-0.5B-quantized.w8a16 Other, 595 downloads
- bnb-community/Qwen2.5-0.5B-bnb-4bit bitsandbytes, 4bit, 125 downloads
- RedHatAI/Qwen2.5-0.5B-quantized.w8a8 Other, w8a8, 123 downloads
- jncraton/Qwen2.5-0.5B-Instruct-ct2-int8 Other, int8, 91 downloads
- ModelCloud/Qwen2.5-0.5B-Instruct-gptqmodel-w4a16 GPTQ, w4a16, 70 downloads
- RedHatAI/Qwen2.5-0.5B-FP8-dynamic FP8, 67 downloads
- osllmai-community/Qwen2.5-0.5B-bnb-4bit bitsandbytes, 4bit, 29 downloads
- CalamitousFelicitousness/Qwen2.5-0.5B-Instruct-fp8-dynamic FP8, 28 downloads
- genovalabs/Qwen2.5-0.5B-Instruct-fp8-dynamic FP8, 18 downloads
- async0x42/Qwen2.5-0.5B-Instruct-exl2_2.0bpw EXL2, 9 downloads
- BondingAI/Qwen2.5-0.5B-awq-4bit AWQ, 4bit, 9 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.
- Qwen/Qwen2.5-0.5B-Instruct494M4.1MReviewed
- Qwen/Qwen2.5-Coder-0.5B494M23kUnreviewed
- mlx-community/Qwen2.5-0.5B-Instruct-4bit23kUnreviewed
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.