whatmodel.sh / Granite 3.1 8B Instruct
Granite 3.1 8B Instruct
↗ share
+ contribute
Granite 3.1 8B Instruct is an open-weights language model from IBM, released December 2024. Its published size is 8.17B parameters and a 128k-token context window. Licence: apache-2.0.
Catalogue identity notes
Arena entry 'granite-3.1-8b-instruct' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'granite-3.1-8b-instruct' as 'Granite-3.1-8B-Instruct' (IBM, Apache 2.0), linking https://huggingface.co/ibm-granite/granite-3.1-8b-instruct. Maker repo ibm-granite/granite-3.1-8b-instruct @4009206: licence tag apache-2.0. 8,170,848,256 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-12: month the maker's Hugging Face repo was created (createdAt 2024-12-06).
$ how it compares
The LLMs ranked either side of Granite 3.1 8B Instruct, out of 828 with a score, then more from IBM.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 576 |  LFM2 2.6B | 43±2 | local | ||
| 577 |  SmolLM3 3B | 43±1 | local | ||
| 578 | Granite 3.1 8B Instruct | 43±1 | local | ||
| 579 |  Llama 3.2 11B Vision Instruct | 43±2 | local | ||
| 580 |  Qwen2.5 3B Instruct | 43±1 | 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
agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #257 of 300 * · 2.9% of its score · 1 test
Beats DeepSeek R1 0528 Qwen3 8B, Magistral Small 1.0 (2506), Llama 4 Scout (109B-A17B) here, though they rank higher overall. Trails Granite 4.0 H 1B, Granite 4.0 1B, Qwen2.5 3B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| BFCL V4 (December 2025 archive) | 27.1% ✎ | ▁▁▁▂██▅▅▆▂▂▂ beats 20/77 | 2.9% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #298 of 393 · 17% of its score · 3 tests
Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, OpenThinker3 7B here, though they rank higher overall. Trails LFM2 350M, Flan-T5 XXL, LFM2 700M here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1208.5 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 72/379 | 8.1% |
| IFEval (aggregation unspecified) lab +1 | 73.2% ✎ | ▄▄·▄······▄█ beats 3/5 | 5.3% |
| Arena-Hard (version/judge unspecified) lab | 37.6% ✎ | █·▄··▄·····█ beats 3/5 | 3.6% |
math▁▂▃▅▆▅▄█▄▁▁▁ #320 of 398 · 30% of its score · 3 tests
Beats Athene-70B, Gemma 2 9B IT, GPT-3.5 Turbo (0125) here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, Tulu 2 DPO 13B here, though they rank lower overall.
other tests9 not in a task · 49% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MMLU lab +1 | 66.8% ✎ | ▄█········▄█ beats 4/5 | 10% |
| ARC Challenge lab | 62.6% ✎ | ▆▁▁▂▂▅▇█▄▃▃▂ beats 74/97 | 9.2% |
| BIG-Bench Hard lab | 69.9% ✎ | █·▄·····▄▄·▄ beats 4/5 | 9.0% |
| DROP lab | 58.6% ✎ | ▃▃·····▃···█ beats 4/5 | 6.3% |
| WinoGrande lab | 75.4% ✎ | ▁···▂▁▁▅█▇▃▁ beats 75/87 | 5.8% |
| HellaSwag lab | 84.5% ✎ | ▁▁▁▁▂▂▃▇█▆▅▃ beats 76/85 | 3.3% |
| PopQA lab | 28.7% ✎ | ▄·█······▄·█ beats 5/5 | 2.9% |
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 72.3% ✎ | ▃▁▁▁▁▁▁▁▂█▅▁ beats 195/276 | 1.8% |
1 more test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 91.4% ✎ | ▁▁▂▃▄▄█▆▃▂▂▁ beats 30/140 | 0.7% |
$ 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 3.1 8B Instruct · needs ~4.9 GB · from huggingface.co/lmstudio-communitychat in the terminal
llama cli -hf lmstudio-community/granite-3.1-8b-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-3.1-8b-instruct-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Granite 3.1 8B Instruct · needs ~4.9 GB · from huggingface.co/lmstudio-community
- Or download it in the terminal
lms get https://huggingface.co/lmstudio-community/granite-3.1-8b-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 Granite 3.1 8B Instruct · needs ~5.4 GB · from ollama.comchat in the terminal
ollama run granite3.1-dense:8b-instruct-q4_K_M
Weights and documentation: huggingface.co/ibm-granite ↗
$ how the score was worked out · ibm-granite/granite-3.3-8b-in… 55%, ibm-granite/granite-3.1-3b-a8… 31%, LMArena leaderboard dataset 8% and 3 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 |
|---|---|---|
 ibm-granite/granite-3.3-8b-instruct model card · lab-reported | 9 | 55% |
| ibm-granite/granite-3.1-3b-a800m-instruct model card · lab-reported | 6 | 31% |
 LMArena leaderboard dataset | 1 | 8% |
| Berkeley Function Calling Leaderboard result archive | 1 | 3% |
| Open Portuguese LLM Leaderboard (archived) | 1 | 2% |
 Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 1 | 1% |
| prior · pull toward the middle | 0% | |
| weighted average | = 42.7 |
$ 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