- 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
- 16 Aug 2024the date the repo was created
- Context length
- 128k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Phi3ForCausalLM
- On Hugging Face
- microsoft/Phi-3.5-mini-instruct304k downloads in the last 30 days, 1.3k likes
Scores
Epoch's name: Phi-3.5-mini-instruct. Best closed model on this set: Inflection-1, 89.7% (Inflection AI). All 136 results
Epoch's name: Phi-3.5-mini-instruct. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results
Epoch's name: Phi-3.5-mini-instruct. Best closed model on this set: gpt-4o-mini-2024-07-18, 88.7% (OpenAI). All 113 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-3.5-mini-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
MaziyarPanahi/Phi-3.5-mini-instruct-GGUF (converted by MaziyarPanahi), 49k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XS | 1.5 GBfile size | 5.0 GB1.5 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:IQ3_XSOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:IQ3_XSDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.IQ3_XS.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q3_K_S | 1.6 GBfile size | 5.1 GB1.6 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q3_K_SOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q3_K_SDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q3_K_S.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q3_K_M | 1.8 GBfile size | 5.3 GB1.8 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q3_K_MOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q3_K_MDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q3_K_M.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| IQ4_XS | 1.9 GBfile size | 5.4 GB1.9 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:IQ4_XSOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:IQ4_XSDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.IQ4_XS.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q3_K_L | 1.9 GBfile size | 5.4 GB1.9 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q3_K_LOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q3_K_LDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q3_K_L.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q4_K_S | 2.0 GBfile size | 5.5 GB2.0 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q4_K_SOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q4_K_SDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q4_K_S.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q4_K_M | 2.2 GBfile size | 5.7 GB2.2 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q4_K_MOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q4_K_MDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q4_K_M.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q5_K_S | 2.5 GBfile size | 6.0 GB2.5 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q5_K_SOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q5_K_SDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q5_K_S.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q5_K_M | 2.6 GBfile size | 6.1 GB2.6 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q5_K_MOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q5_K_MDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q5_K_M.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q6_K | 2.9 GBfile size | 6.4 GB2.9 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q6_KOllama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q6_KDownload hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q6_K.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
| Q8_0 | 3.8 GBfile size | 7.3 GB3.8 + 3.0 + 0.50 | Commandsllama.cpp llama-server -hf MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q8_0Ollama ollama run hf.co/MaziyarPanahi/Phi-3.5-mini-instruct-GGUF:Q8_0Download hf download MaziyarPanahi/Phi-3.5-mini-instruct-GGUF --include "Phi-3.5-mini-instruct.Q8_0.gguf" --local-dir Phi-3.5-mini-instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXplawanrath/phi-3.5-mini-instruct-q4-mlx-cba | 2.0 GBfile size | 5.5 GB2.0 + 3.0 + 0.50 | Download page |
| MLXplawanrath/phi-3.5-mini-instruct-q8-mlx-cba | 3.8 GBfile size | 7.3 GB3.8 + 3.0 + 0.50 | Download page |
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-3.5-mini-instruct --local-dir Phi-3.5-mini-instructOther conversions (8; sizes not read)
- unsloth/Phi-3.5-mini-instruct-bnb-4bit bitsandbytes, 4bit, 4.4k downloads
- mlc-ai/Phi-3.5-mini-instruct-q4f16_1-MLC Other, 3.8k downloads
- mlc-ai/Phi-3.5-mini-instruct-q4f16_0-MLC Other, 2.0k downloads
- OpenVINO/Phi-3.5-mini-instruct-int4-cw-ov Other, int4, 1.1k downloads
- OpenVINO/Phi-3.5-mini-instruct-int4-ov Other, int4, 874 downloads
- RedHatAI/Phi-3.5-mini-instruct-FP8-KV FP8, 61 downloads
- simaai/Phi-3.5-mini-instruct-Autoround-Safetensors GPTQ, 28 downloads
- liodon-ai/Phi-3.5-mini-instruct-FP8 FP8, 27 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.
- microsoft/MediPhi-Instruct3.8B2.9kUnreviewed
- microsoft/MediPhi-PubMed3.8B2.6kUnreviewed
- microsoft/MediPhi3.8B2.5kUnreviewed
- microsoft/MediPhi-Clinical3.8B1.0kUnreviewed
- microsoft/MediPhi-MedCode3.8B733Unreviewed
- microsoft/MediPhi-Guidelines3.8B713Unreviewed
- microsoft/MediPhi-MedWiki3.8B310Unreviewed
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.