whatmodel.sh / Gemma 1.1 2B IT
Gemma 1.1 2B IT
↗ share
+ contribute
Gemma 1.1 2B IT is an open-weights language model from Google, released April 2024. Its published size is 2.51B parameters and a 8k-token context window. Licence: gemma.
Catalogue identity notes
Arena entry 'gemma-1.1-2b-it' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'gemma-1.1-2b-it' as 'Gemma-1.1-2b-it' (Google, Gemma license), linking https://huggingface.co/google/gemma-1.1-2b-it. Maker repo google/gemma-1.1-2b-it @d750f5e: licence tag gemma. 2,506,172,416 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: Google Gemma releases page (ai.google.dev/gemma/docs/releases): 'April 5, 2024 Release of Gemma 1.1'.
$ how it compares
The LLMs ranked either side of Gemma 1.1 2B IT, out of 828 with a score, then more from Google.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 747 | Gemma 2B (base) | 29±1 | local | ||
| 748 |  OpenLLaMA 7B v2 | 29±1 | local | ||
| 749 | Gemma 1.1 2B IT | 29±1 | local | ||
| 750 |  StableLM-Base-Alpha 7B v2 | 29±1 | local | ||
| 751 |  Granite 3.1 1B-A400M Instruct | 29±2 | local | ||
| more from Google | |||||
| 9 |  Gemini 4 Argon (limited preview) | 82±1 | limited preview | ||
| 23 | Gemini 3.8 Flash | 77±1 | api $1.50/M | ||
| 32 | Gemini 3.7 Flash | 76±1 | api $1.50/M | ||
$ what it's good at
coding▁▁▁▃▆██▇▆▄▃▁ #440 of 458 · 80% of its score · 3 tests
Beats Molmo 7B-D (0924), DeepSeek R1 Distill Qwen 1.5B, Tulu 2 7B here, though they rank higher overall. Trails Falcon3 1B Instruct, Granite 3.0 1B-A400M Instruct here, though they rank lower overall.
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #372 of 393 · 15% of its score · 3 tests
Beats Phi-2 (2.7B), Qwen2.5 1.5B Instruct, Nous-Hermes-13b here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024) | 1044.0 ✎ | ▂▁▂▁▃▇█▆▇▄▂▂ beats 24/95 | 6.8% |
| LMArena (text) | 1116.6 ✎ | ▁▁▁▃▃▃▃▆▆▇█▃ beats 21/379 | 6.7% |
| Arena-Hard (v0.1, GPT-4-1106 judge) | 3.4% ✎ | ▃▁▁▅█▅▄▃▃▅▃▁ beats 1/60 | 2.0% |
other tests3 not in a task · 4.6% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Polish EQ-Bench v2 (SpeakLeash) | 16.5% ✎ | ▁··▃▁▂▂▆▅▆█▆ beats 2/70 | 2.7% |
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 35.5% ✎ | ▃▁▁▃▁▁▁▁▂█▅▁ beats 42/276 | 1.0% |
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 72.2% ✎ | ▃▁▂▃▄▄█▆▃▂▂▁ beats 1/140 | 0.9% |
$ 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 Gemma 1.1 2B IT · needs ~1.6 GB · from huggingface.co/lmstudio-communitychat in the terminal
llama cli -hf lmstudio-community/gemma-1.1-2b-it-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf lmstudio-community/gemma-1.1-2b-it-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Gemma 1.1 2B IT · needs ~1.6 GB · from huggingface.co/lmstudio-community
- Or download it in the terminal
lms get https://huggingface.co/lmstudio-community/gemma-1.1-2b-it-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 Gemma 1.1 2B IT · needs ~2.01 GB · from ollama.comchat in the terminal
ollama run gemma:2b-instruct-v1.1-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 Gemma 1.1 2B IT · needs ~2.2 GB, Mac only · from huggingface.co/mlx-communitychat in the terminal
mlx_lm.chat --model mlx-community/gemma-1.1-2b-it-4bit - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/gemma-1.1-2b-it-4bit
Official weights and documentation: huggingface.co/google ↗
$ how the score was worked out · EvalPlus / EvalPerf published… 80%, Polyrating: A Cost-Effective… 7%, LMArena leaderboard dataset 7% and 4 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 |
|---|---|---|
 EvalPlus / EvalPerf published evaluation runs | 3 | 80% |
 Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3) | 1 | 7% |
 LMArena leaderboard dataset | 1 | 7% |
| SpeakLeash Polish EQ-Bench leaderboard | 1 | 3% |
 Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2) | 1 | 2% |
| Open Portuguese LLM Leaderboard (archived) | 1 | 1% |
| Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 1 | 1% |
| prior · pull toward the middle | 0% | |
| weighted average | = 28.8 |
$ 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