- Size
- 3.8B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, MIT LicenseOur 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
- 22 Apr 2024the date the repo was created
- Context length
- 4k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Phi3ForCausalLM
- On Hugging Face
- microsoft/Phi-3-mini-4k-instruct317k downloads in the last 30 days, 1.5k likes
Scores
- default setting52.8%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: gpt-3.5-turbo-1106, 58.1% (OpenAI). All 15 results
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: gpt-3.5-turbo-1106, 87.4% (OpenAI). All 134 results
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: gemini-1.5-pro-001, 89.2% (Google DeepMind). All 88 results
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: gpt-4-0314, 95.3% (OpenAI). All 113 results
- default setting22.4%LiveBench Leaderboard
- default setting22.1%LiveBench Leaderboard
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: gemini-2.5-pro-exp-03-25, 82.3% (Google DeepMind). All 54 results
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
- Shots: 1088.0%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 1083.2%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 1083.2%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: gpt-3.5-turbo-1106, 86.0% (OpenAI). All 70 results
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: claude-2.0, 87.5% (Anthropic). All 115 results
Epoch's name: Phi-3-mini-4k-instruct. Best closed model on this set: claude-3-opus-20240229, 88.5% (Anthropic). All 137 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: 3.0 GB, worked out from the model's config (microsoft/Phi-3-mini-4k-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
legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF (converted by legraphista), 6.3k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 1.4 GBfile size | 4.9 GB1.4 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_XXSOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_XXSDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.IQ3_XXS.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| IQ3_XS | 1.5 GBfile size | 5.0 GB1.5 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_XSOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_XSDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.IQ3_XS.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| IQ3_S | 1.6 GBfile size | 5.1 GB1.6 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_SOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_SDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.IQ3_S.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q3_K_S | 1.6 GBfile size | 5.1 GB1.6 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q3_K_SOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q3_K_SDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q3_K_S.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| IQ3_M | 1.7 GBfile size | 5.2 GB1.7 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_MOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ3_MDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.IQ3_M.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q3_K | 1.8 GBfile size | 5.3 GB1.8 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q3_KOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q3_KDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q3_K.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| IQ4_XS | 1.9 GBfile size | 5.4 GB1.9 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ4_XSOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ4_XSDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.IQ4_XS.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q3_K_L | 1.9 GBfile size | 5.4 GB1.9 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q3_K_LOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q3_K_LDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q3_K_L.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| IQ4_NL | 2.0 GBfile size | 5.5 GB2.0 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ4_NLOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:IQ4_NLDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.IQ4_NL.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q4_K_S | 2.0 GBfile size | 5.5 GB2.0 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q4_K_SOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q4_K_SDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q4_K_S.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q4_K | 2.2 GBfile size | 5.7 GB2.2 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q4_KOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q4_KDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q4_K.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q5_K_S | 2.5 GBfile size | 6.0 GB2.5 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q5_K_SOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q5_K_SDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q5_K_S.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q5_K | 2.6 GBfile size | 6.1 GB2.6 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q5_KOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q5_KDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q5_K.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q6_K | 2.9 GBfile size | 6.4 GB2.9 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q6_KOllama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q6_KDownload hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q6_K.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| Q8_0 | 3.8 GBfile size | 7.3 GB3.8 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q8_0Ollama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:Q8_0Download hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.Q8_0.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| BF16 | 7.1 GBfile size | 10.6 GB7.1 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:BF16Ollama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:BF16Download hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.BF16.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
| F16 | 7.1 GBfile size | 10.6 GB7.1 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:F16Ollama ollama run hf.co/legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF:F16Download hf download legraphista/Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF --include "Phi-3-mini-4k-instruct.FP16.gguf" --local-dir Phi-3-mini-4k-instruct-update2024_07_03-IMat-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 7.1 GBfile size | 10.6 GB7.1 + 3.0 + 0.50 |
hf download microsoft/Phi-3-mini-4k-instruct --local-dir Phi-3-mini-4k-instructOther conversions (8; sizes not read)
- OpenVINO/Phi-3-mini-4k-instruct-int4-ov Other, int4, 1.7k downloads
- mlc-ai/Phi-3-mini-4k-instruct-q4f16_1-MLC Other, 1.0k downloads
- mlc-ai/Phi-3-mini-4k-instruct-q4f32_1-MLC Other, 209 downloads
- litert-community/Phi-3-mini-4k-instruct Other, 83 downloads
- amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-fp16-onnx-hybrid AWQ, int4, 42 downloads
- solidrust/Phi-3-mini-4k-instruct-AWQ AWQ, 34 downloads
- leliuga/Phi-3-mini-4k-instruct-bnb-4bit bitsandbytes, 4bit, 30 downloads
- amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix AWQ, int4, 29 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.
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.