whatmodel.sh / Phi-3-mini-4k-instruct (June 2024 update)
Phi-3-mini-4k-instruct (June 2024 update)
↗ share
+ contribute
Phi-3-mini-4k-instruct (June 2024 update) is an open-weights language model from Microsoft, released June 2024. Its published size is 3.82B parameters. Licence: mit.
Catalogue identity notes
Comparison-only. Arena entry 'phi-3-mini-4k-instruct-june-2024' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'phi-3-mini-4k-instruct-june-2024' as 'Phi-3-Mini-4K-Instruct-June-24' (Microsoft, MIT), linking https://huggingface.co/microsoft/Phi-3-mini-4k-instruct. Maker repo microsoft/Phi-3-mini-4k-instruct @f39ac1d: licence tag mit. 3,821,079,552 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-06: card: 'Release dates: June, 2024' ('June 2024 Update'). LMArena labels it 'Phi-3-Mini-4K-Instruct-June-24'. The current HF repo revision is this update; no ollama tag states its version.
$ how it compares
The LLMs ranked either side of Phi-3-mini-4k-instruct (June 2024 update), out of 828 with a score, then more from Microsoft.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 538 |  Mistral NeMo Instruct (2407) | 44±1 | local | ||
| 539 |  LLaVA-OneVision Qwen2 72B (ov-sft) | 44±3 | local | ||
| 540 | Phi-3-mini-4k-instruct (June 2024 update) | 44±1 | local | ||
| 541 |  Yi 1.5 9B Chat | 44±1 | local | ||
| 542 |  Command R7B (12-2024) | 44±1 | local | ||
| more from Microsoft | |||||
| 252 | Phi-4-reasoning-plus 14B | 59±1 | local | ||
| 261 | Phi-4-reasoning 14B | 58±1 | api $0.22/M +local | ||
| 365 | Phi-4 14B | 53±1 | api $0.087/M +local | ||
$ what it's good at
coding▁▁▁▃▆██▇▆▄▃▁ #324 of 458 * · 22% of its score · 1 test
Beats GLM-4.7-Flash, Qwen3-VL 8B Instruct, Qwen3-VL 4B Instruct here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CRUXEval (ZeroEval, 800 problems) | 44.8% ✎ | ▁▂▆▃▆█▆▃▂·▁▁ beats 8/47 | 22% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #356 of 393 * · 7.7% of its score · 1 test
Beats Gemma 4 E2B, Code Llama 70B Instruct here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Qwen2.5 0.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1143.1 ✎ | ▁▁▁▃▃▃▃▆▆▇█▃ beats 35/379 | 7.7% |
math▁▂▃▅▆▅▄█▄▁▁▁ #349 of 398 * · 22% of its score · 2 tests
Beats Command R Plus (04-2024) here, though they rank higher overall. Trails Qwen3 0.6B, Tulu 2 DPO 7B, Gemma 7B (base) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GSM8K (ZeroEval, zero-shot) | 75.5% ✎ | ▁▄·▁▄█▅▅▅███ beats 6/43 | 15% |
| MATH Level 5 (ZeroEval, 721 problems) | 16.2% ✎ | ▁▁▁▆█▂▇▇▄··▂ beats 4/38 | 7.2% |
other tests3 not in a task · 47% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MMLU-Redux (ZeroEval, 2,778 questions) | 70.3% ✎ | ▁·▁▁▄▄▄▅█▄▂▁ beats 15/53 | 40% |
| ZebraLogic (ZeroEval, 1,000 puzzles) | 11.6% ✎ | ▁▁▃▆██▁▁·▁▁▁ beats 12/57 | 6.4% |
| EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy | 80.2% ✎ | ▁▁▁▁▁▁▁▂▄█▄▃ beats 67/146 | 1.1% |
$ where to run it
llama.cpp · recommended
version
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run Phi-3-mini-4k-instruct (June 2024 update) · needs ~2.39 GB · from huggingface.co/bartowskichat in the terminal
llama cli -hf bartowski/Phi-3.1-mini-4k-instruct-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/Phi-3.1-mini-4k-instruct-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Phi-3-mini-4k-instruct (June 2024 update) · needs ~2.39 GB · from huggingface.co/bartowski
- Or download it in the terminal
lms get https://huggingface.co/bartowski/Phi-3.1-mini-4k-instruct-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Phi-3-mini-4k-instruct (June 2024 update) · needs ~2.39 GB · from huggingface.co/bartowskichat in the terminal
ollama run hf.co/bartowski/Phi-3.1-mini-4k-instruct-GGUF:Q4_K_M
MLX (Mac)
version
- Install MLX (Mac) · Apple silicon Macs only, text only.with uv
uv tool install mlx-lmorpip install mlx-lm - Run Phi-3-mini-4k-instruct (June 2024 update) · needs ~2.1 GB, Mac only · from huggingface.co/mlx-communitychat in the terminal
mlx_lm.chat --model mlx-community/Phi-3-mini-4k-instruct-4bit - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/Phi-3-mini-4k-instruct-4bit
Official weights and documentation: huggingface.co/microsoft ↗
$ how the score was worked out · WildEval ZeroEval published r… 91%, LMArena leaderboard dataset 8%, EuroEval leaderboards (result… 1%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 WildEval ZeroEval published results | 5 | 91% |
 LMArena leaderboard dataset | 1 | 8% |
 EuroEval leaderboards (results collection), English generative leaderboard | 1 | 1% |
| prior · pull toward the middle | 0% | |
| weighted average | = 44.2 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json