whatmodel.sh / InternLM2.5 20B Chat
InternLM2.5 20B Chat
↗ share
+ contribute
InternLM2.5 20B Chat is an open-weights language model from Shanghai AI Laboratory (InternLM), released August 2024. Its published size is 19.9B parameters and a 33k-token context window. Licence: other.
Catalogue identity notes
Arena entry 'internlm2_5-20b-chat' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'internlm2_5-20b-chat' as 'InternLM2.5-20B-chat' (InternLM, Other), linking https://huggingface.co/internlm/internlm2_5-20b-chat. Maker repo internlm/internlm2_5-20b-chat @1374122: licence tag other. 19,861,149,696 parameters from the Hugging Face safetensors metadata (dense, so active = total).
Model information sources
$ how it compares
The LLMs ranked either side of InternLM2.5 20B Chat, out of 828 with a score, then more from Shanghai AI Laboratory (InternLM).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 518 |  OpenChat 3.5 0106 Gemma | 46±3 | local | ||
| 519 |  Olmo 3 7B Instruct | 46±1 | local | ||
| 520 | InternLM2.5 20B Chat | 46±2 | local | ||
| 521 |  StarCoder2-15B-Instruct-v0.1 | 46±1 | local | ||
| 522 |  Qwen1.5 72B Chat | 45±1 | local | ||
| more from Shanghai AI Laboratory (InternLM) | |||||
| 446 | InternLM2.5 7B Chat | 49±2 | local | ||
| 486 | InternLM2.5 7B Chat 1M | 47±4 | local | ||
| 609 | InternLM2 Chat 20B | 41±1 | local | ||
$ what it's good at
coding▁▁▁▃▆██▇▆▄▃▁ #232 of 458 · 16% of its score · 4 tests
Beats Qwen3.5 4B, Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B) here, though they rank higher overall. Trails QwQ-32B-Preview here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CodeReviewQA: solution identification (hard), invariant accuracy | 70.7% ✎ | ▃··▁▂▂▃▂█▃▄▂ beats 38/47 | 6.0% |
| CodeReviewQA: change localisation (hard), invariant accuracy | 55.3% ✎ | █▂▁▁▂▂▂▃▅▅▅▇ beats 38/47 | 5.7% |
| CodeReviewQA: automated code refinement, exact match rate | 33.4% ✎ | ▁▁▁▁▁▁▂▂▃█▅▄ beats 32/47 | 4.3% |
| CodeReviewQA: change type recognition, invariant accuracy | 75.7% ✎ | ▁▁▁······▁▃█ beats 30/47 | 0.1% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #309 of 393 * · 78% of its score · 2 tests
Beats Gemma 4 E4B, OpenThinker3 7B, Gemma 4 E2B here, though they rank higher overall. Trails LFM2 350M, Gemma 3 1B, Flan-T5 XXL here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena-Hard (v0.1, GPT-4-1106 judge) | 31.2% ✎ | ▂▁▁▅█▅▄▃▃▅▃▁ beats 26/60 | 56% |
| LMArena (text) | 1190.7 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 64/379 | 22% |
other tests1 not in a task · 5.0% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 56.9% ✎ | ▃▁▁▁▁▁▁▁▃█▅▁ beats 81/276 | 5.0% |
$ 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 InternLM2.5 20B Chat · needs ~12 GB · from huggingface.co/lmstudio-communitychat in the terminal
llama cli -hf lmstudio-community/internlm2_5-20b-chat-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf lmstudio-community/internlm2_5-20b-chat-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run InternLM2.5 20B Chat · needs ~12 GB · from huggingface.co/lmstudio-community
- Or download it in the terminal
lms get https://huggingface.co/lmstudio-community/internlm2_5-20b-chat-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 InternLM2.5 20B Chat · needs ~12.44 GB · from ollama.comchat in the terminal
ollama run internlm2:20b-chat-v2.5-q4_K_M
MLX (Mac)
- Install MLX (Mac) · Apple silicon Macs only, text only.with uv
uv tool install mlx-lmorpip install mlx-lm - Run InternLM2.5 20B Chat · needs ~21.1 GB, Mac only · from huggingface.co/mlx-communitychat in the terminal
mlx_lm.chat --model mlx-community/internlm2_5-20b-chat_8bit - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/internlm2_5-20b-chat_8bit
Official weights and documentation: huggingface.co/internlm ↗
$ how the score was worked out · Arena-Hard-Auto v0.1 leaderbo… 56%, LMArena leaderboard dataset 22%, CodeReviewQA: The Code Review… 16% and 1 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 |
|---|---|---|
 Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2) | 1 | 56% |
 LMArena leaderboard dataset | 1 | 22% |
 CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2) | 4 | 16% |
 Open Portuguese LLM Leaderboard (archived) | 1 | 5% |
| prior · pull toward the middle | 1% | |
| weighted average | = 45.5 |
$ 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