- Size
- 1.4B 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
- 10 Sep 2023the date the repo was created
- Context length
- 2k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)PhiForCausalLM
- On Hugging Face
- microsoft/phi-1_550k downloads in the last 30 days, 1.4k likes
Scores
- default setting44.4%Textbooks Are All You Need II: phi-1.5 technical report
Epoch's name: phi-1_5. Best closed model on this set: gpt-3.5-turbo-1106, 87.4% (OpenAI). All 134 results
Epoch's name: phi-1_5. Best closed model on this set: Inflection-1, 89.7% (Inflection AI). All 136 results
Epoch's name: phi-1_5. Best closed model on this set: gpt-4-0314, 95.3% (OpenAI). All 113 results
Epoch's name: phi-1_5. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
Epoch's name: phi-1_5. Best closed model on this set: gpt-3.5-turbo-1106, 86.0% (OpenAI). All 70 results
Epoch's name: phi-1_5. 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: 1.5 GB, worked out from the model's config (microsoft/phi-1_5), 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/phi-1_5-GGUF (converted by mradermacher), 457 downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 0.54 GBfile size | 2.5 GB0.54 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q2_KOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q2_KDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q2_K.gguf" --local-dir phi-1_5-GGUF |
| Q3_K_S | 0.61 GBfile size | 2.6 GB0.61 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q3_K_SOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q3_K_SDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q3_K_S.gguf" --local-dir phi-1_5-GGUF |
| Q3_K_M | 0.69 GBfile size | 2.7 GB0.69 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q3_K_MOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q3_K_MDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q3_K_M.gguf" --local-dir phi-1_5-GGUF |
| IQ4_XS | 0.74 GBfile size | 2.7 GB0.74 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:IQ4_XSOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:IQ4_XSDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.IQ4_XS.gguf" --local-dir phi-1_5-GGUF |
| Q3_K_L | 0.75 GBfile size | 2.8 GB0.75 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q3_K_LOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q3_K_LDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q3_K_L.gguf" --local-dir phi-1_5-GGUF |
| Q4_K_S | 0.78 GBfile size | 2.8 GB0.78 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q4_K_SOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q4_K_SDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q4_K_S.gguf" --local-dir phi-1_5-GGUF |
| Q4_K_M | 0.83 GBfile size | 2.8 GB0.83 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q4_K_MOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q4_K_MDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q4_K_M.gguf" --local-dir phi-1_5-GGUF |
| Q5_K_S | 0.92 GBfile size | 2.9 GB0.92 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q5_K_SOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q5_K_SDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q5_K_S.gguf" --local-dir phi-1_5-GGUF |
| Q5_K_M | 0.96 GBfile size | 3.0 GB0.96 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q5_K_MOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q5_K_MDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q5_K_M.gguf" --local-dir phi-1_5-GGUF |
| Q6_K | 1.1 GBfile size | 3.1 GB1.1 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q6_KOllama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q6_KDownload hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q6_K.gguf" --local-dir phi-1_5-GGUF |
| Q8_0 | 1.4 GBfile size | 3.4 GB1.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:Q8_0Ollama ollama run hf.co/mradermacher/phi-1_5-GGUF:Q8_0Download hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.Q8_0.gguf" --local-dir phi-1_5-GGUF |
| F16 | 2.6 GBfile size | 4.6 GB2.6 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/phi-1_5-GGUF:F16Ollama ollama run hf.co/mradermacher/phi-1_5-GGUF:F16Download hf download mradermacher/phi-1_5-GGUF --include "phi-1_5.f16.gguf" --local-dir phi-1_5-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F16original weights | 2.6 GBfile size | 4.6 GB2.6 + 1.5 + 0.50 |
hf download microsoft/phi-1_5 --local-dir phi-1_5Other conversions (4; sizes not read)
- mlc-ai/phi-1_5-q4f16_1-MLC Other, 351 downloads
- mlc-ai/phi-1_5-q4f32_1-MLC Other, 97 downloads
- BricksDisplay/phi-1_5-q4 Other, 27 downloads
- mlc-ai/phi-1_5-q0f32-MLC Other, 12 downloads
The Hub tags 36 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.