whatmodel.sh / Phi-3 Medium 128K Instruct
Phi-3 Medium 128K Instruct
↗ share
+ contribute
Phi-3 Medium 128K Instruct is an open-weights language model from Microsoft, released April 2024. Its published size is 13.96B parameters and a 128k-token context window. Licence: mit.
Catalogue identity notes
Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2024-04-23). Exact checkpoint Phi-3-medium-128k-instruct (not the 4k variant). The Hugging Face repo has no weight updates after the May 2024 upload (commit history). 13,960,238,080 parameters.
$ how it compares
The LLMs ranked either side of Phi-3 Medium 128K Instruct, out of 828 with a score, then more from Microsoft.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 525 |  Claude 2.0 | 45±1 | comparison only | ||
| 526 |  OpenThinker 7B | 45±2 | local | ||
| 527 | Phi-3 Medium 128K Instruct | 45±1 | local | ||
| 528 |  QwQ-32B-Preview | 45±2 | local | ||
| 529 |  DeepSeek-Coder-V2 Lite Instruct (16B-A2.4B) | 45±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▁▁▁▃▆██▇▆▄▃▁ #256 of 458 · 10% of its score · 4 tests
Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, QwQ-32B-Preview here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CodeReviewQA: solution identification (hard), invariant accuracy | 50.8% ✎ | ▃··▁▂▂▃▂█▃▄▂ beats 26/47 | 3.7% |
| CodeReviewQA: change localisation (hard), invariant accuracy | 43.0% ✎ | █▂▁▁▂▂▂▃▅▅▅▇ beats 32/47 | 3.5% |
| CodeReviewQA: automated code refinement, exact match rate | 30.2% ✎ | ▁▁▁▁▁▁▂▂▃█▅▄ beats 20/47 | 2.6% |
| CodeReviewQA: change type recognition, invariant accuracy | 76.7% ✎ | ▁▁▁······▁▃█ beats 37/47 | 0.1% |
math▁▂▃▅▆▅▄█▄▁▁▁ #328 of 398 * · 18% of its score · 1 test
Beats GPT-3.5 Turbo (0125), Qwen2-VL 7B Instruct, DBRX Instruct here, though they rank higher overall. Trails Qwen3 0.6B, Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MATH level 5 | 17.6% ✎ | ▂▂▅▆▄█▆▃▅▂▃▄ beats 15/92 | 18% |
other tests5 not in a task · 71% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LiveBench 2024-07-26 | 30.3% ✎ | ▁▁▁▂▂▃▂█▆▃▅▃ beats 28/61 | 53% |
| GPQA Diamond | 27.6% ✎ | ▁▁▃▁▂▄▆▄▅▇█▅ beats 12/208 | 10% |
| RULER 64k | 78.6% ✎ | ▁▁·▁·▂▃▄█▂·▁ beats 5/22 | 3.6% |
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 71.7% ✎ | ▃▁▁▁▁▁▁▁▂█▅▁ beats 188/276 | 3.1% |
| RULER 128k | 46.1% ✎ | ▄··▂▄▂▆██▄▄▂ beats 3/21 | 1.3% |
$ 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 Medium 128K Instruct · needs ~8.6 GB · from huggingface.co/bartowskichat in the terminal
llama cli -hf bartowski/Phi-3-medium-128k-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-medium-128k-instruct-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Phi-3 Medium 128K Instruct · needs ~8.6 GB · from huggingface.co/bartowski
- Or download it in the terminal
lms get https://huggingface.co/bartowski/Phi-3-medium-128k-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 Medium 128K Instruct · needs ~8.88 GB · from ollama.comchat in the terminal
ollama run phi3:medium-128k
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 Medium 128K Instruct · needs ~7.9 GB, Mac only · from huggingface.co/mlx-communitychat in the terminal
mlx_lm.chat --model mlx-community/Phi-3-medium-128k-instruct-4bit - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/Phi-3-medium-128k-instruct-4bit
Official weights and documentation: huggingface.co/microsoft ↗
$ how the score was worked out · LiveBench model judgments (HF… 53%, Epoch AI — internal evaluatio… 29%, CodeReviewQA: The Code Review… 10% and 2 more
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 |
|---|---|---|
 LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets | 1 | 53% |
 Epoch AI — internal evaluations | 2 | 29% |
 CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2) | 4 | 10% |
 NVIDIA RULER repository README results table | 2 | 5% |
| Open Portuguese LLM Leaderboard (archived) | 1 | 3% |
| prior · pull toward the middle | 1% | |
| weighted average | = 45.1 |
$ 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