whatmodel.sh / Granite 3.0 1B-A400M Instruct
Granite 3.0 1B-A400M Instruct
↗ share
+ contribute
Granite 3.0 1B-A400M Instruct is an open-weights language model from IBM, released October 2024. Its published size is 1.3B parameters (0.4B active per token) and a 4k-token context window. Licence: apache-2.0.
Catalogue identity notes
IBM granite-3.0-1b-a400m-instruct (ibm-granite/granite-3.0-1b-a400m-instruct @ffec3c3, created 2024-10-03, apache-2.0, 1,334,628,352 params; card '# Parameters 1.3B', '# Active Parameters 400M'). Lab rows from the Granite 3.0 paper Table 11 (MoE instruction models, IBM's harness, with the catalogued Llama-3.2 1B column) joining the existing Table-10 runs of that source; independent EuroEval rows.
Model information sources
Release date ↗ · Weights licence ↗
Card architecture table '# Parameters 1.3B' / '# Active Parameters 400M' (HF safetensors metadata 1,334,628,352).
$ how it compares
The LLMs ranked either side of Granite 3.0 1B-A400M Instruct, out of 828 with a score, then more from IBM.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 758 |  Koala 13B | 28±1 | comparison only | ||
| 759 |  StarCoderBase 3B | 28±1 | local | ||
| 760 | Granite 3.0 1B-A400M Instruct | 27±1 | local | ||
| 761 |  RedPajama-INCITE 7B Base | 27±1 | local | ||
| 762 |  ChatGLM3-6B | 27±2 | local | ||
| more from IBM | |||||
| 192 | Granite 4.2 30B | 63±1 | api $0.28/M +local | ||
| 239 | Granite 4.2 8B | 60±1 | api $0.11/M +local | ||
| 276 | Granite 4.2 3B | 57±1 | api $0.052/M +local | ||
$ what it's good at
coding▁▁▁▃▆██▇▆▄▃▁ #432 of 458 * · 16% of its score · 2 tests
Beats Qwen3.5 2B, Molmo 7B-D (0924), DeepSeek R1 Distill Qwen 1.5B here, though they rank higher overall.
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #374 of 393 * · 4.3% of its score · 1 test
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 |
|---|---|---|---|
| IFEval (aggregation unspecified) lab | 32.4% ✎ | ▄····█·▄··██ beats 0/7 | 4.3% |
math▁▃▃▅▆▅▄█▄▁▁▁ #390 of 398 * · 16% of its score · 2 tests
Beats Code Llama 7B (base), Llama 2 13B Chat, DeepSeek-Coder 1.3B Base here, though they rank higher overall. Trails Qwen2 0.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GSM8K lab | 26.3% ✎ | █▄····▄··█▄▄ beats 1/7 | 8.8% |
| MATH (subset unspecified) lab | 10.9% ✎ | ▄···▄▄▄▄··█▄ beats 0/7 | 6.7% |
other tests11 not in a task · 63% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| WinoGrande lab | 61.2% ✎ | █···▄▄▄▄···█ beats 1/7 | 10% |
| BIG-Bench Hard lab | 31.8% ✎ | ▃▃···▃··█··▅ beats 0/7 | 10% |
| HellaSwag lab | 65.6% ✎ | ▄·▄··█▄·▄·▄▄ beats 1/7 | 8.6% |
| MMLU lab | 32.0% ✎ | ▄····▄·▄▄█·█ beats 0/7 | 8.2% |
| BoolQ lab | 70.1% ✎ | ▄▄····▄▄·█·█ beats 1/7 | 8.0% |
| MMLU-Pro lab | 12.2% ✎ | ▄·····█··█▄█ beats 0/7 | 5.0% |
| GPQA (subset unspecified) lab | 23.1% ✎ | ▄·▄··▄··▄█·█ beats 0/7 | 4.0% |
| ARC Challenge lab | 41.2% ✎ | ▄····█··▄▄▄█ beats 1/7 | 3.3% |
3 more tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| OpenBookQA lab | 38.4% ✎ | ▄▄··▄··▄·█▄▄ beats 2/7 | 3.1% |
| EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy | 34.8% ✎ | ▁▁▁▁▃▁▁▂▄█▄▃ beats 10/146 | 1.6% |
| Social IQA lab | 47.5% ✎ | ▃·····▃··█▃▅ beats 1/7 | 1.2% |
$ 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 Granite 3.0 1B-A400M Instruct · needs ~0.8 GB · from huggingface.co/lmstudio-communitychat in the terminal
llama cli -hf lmstudio-community/granite-3.0-1b-a400m-instruct-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf lmstudio-community/granite-3.0-1b-a400m-instruct-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Granite 3.0 1B-A400M Instruct · needs ~0.8 GB · from huggingface.co/lmstudio-community
- Or download it in the terminal
lms get https://huggingface.co/lmstudio-community/granite-3.0-1b-a400m-instruct-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Granite 3.0 1B-A400M Instruct · needs ~0.822 GB · from ollama.comchat in the terminal
ollama run granite3-moe:1b
Weights and documentation: huggingface.co/ibm-granite ↗
$ how the score was worked out · IBM Granite 3.0 Language Mode… 98%, EuroEval leaderboards (result… 2%
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 |
|---|---|---|
 IBM Granite 3.0 Language Models technical report (GitHub) · lab-reported | 15 | 98% |
| EuroEval leaderboards (results collection), English generative leaderboard | 1 | 2% |
| prior · pull toward the middle | 1% | |
| weighted average | = 27.3 |
$ 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