whatmodel.sh / Granite 3.2 8B Instruct
Granite 3.2 8B Instruct
↗ share
+ contribute
Granite 3.2 8B Instruct is an open-weights language model from IBM, released February 2025. Its published size is 8.17B parameters and a 131k-token context window. Licence: apache-2.0.
Catalogue identity notes
Maker repo ibm-granite/granite-3.2-8b-instruct @610d8c6: licence tag apache-2.0. 8,170,848,256 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2025-02: month the maker's Hugging Face repo was created (createdAt 2025-02-17). Ollama tags granite3.2:8b-instruct-q4_K_M, granite3.2:8b-instruct-q8_0 are the library's instruct/chat builds of this checkpoint (tag names on the pinned tags page); download sizes are estimated from the parameter count.
$ how it compares
The LLMs ranked either side of Granite 3.2 8B Instruct, out of 828 with a score, then more from IBM.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 559 |  Phi-4-mini 3.8B | 44±1 | api $0.13/M +local | ||
| 560 |  Ministral 8B (2410) | 44±1 | local | ||
| 561 | Granite 3.2 8B Instruct | 44±1 | local | ||
| 562 |  Code Llama 70B Python | 44±1 | local | ||
| 563 | Llama 3.1 8B (base) | 44±3 | 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▁▁▃▆█▆▅▅▅▄▃▁ #259 of 300 * · 5.1% 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) | 26.9% ✎ | ▁▁▁▂██▅▅▆▂▂▂ beats 18/77 | 5.1% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #270 of 393 * · 11% of its score · 2 tests
Beats Ministral 3 14B Reasoning 2512, Ministral 3 14B, Gemma 4 E4B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 1.2B, Granite 4.0 H 1B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena-Hard (version/judge unspecified) lab | 55.3% ✎ | █·▄··▄·····█ beats 4/5 | 6.2% |
| IFEval (aggregation unspecified) lab | 74.3% ✎ | ▄▄·▄······▄█ beats 4/5 | 5.2% |
math▁▂▃▅▆▅▄█▄▁▁▁ #315 of 398 · 39% of its score · 3 tests
Beats Athene-70B, OLMo 2 32B Instruct (0325), Gemma 2 9B IT 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 tests5 not in a task · 44% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| BIG-Bench Hard lab | 71.9% ✎ | █·▄·····▄▄·▄ beats 5/5 | 15% |
| MMLU lab | 66.8% ✎ | ▄█········▄█ beats 5/5 | 12% |
| DROP lab | 58.3% ✎ | ▃▃·····▃···█ beats 3/5 | 11% |
| PopQA lab | 28.0% ✎ | ▄·█······▄·█ beats 4/5 | 5.0% |
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 91.3% ✎ | ▁▁▂▃▄▄█▆▃▂▂▁ beats 29/140 | 1.1% |
$ 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 3.2 8B Instruct · needs ~4.9 GB · from huggingface.co/lmstudio-communitychat in the terminal
llama cli -hf lmstudio-community/granite-3.2-8b-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-3.2-8b-instruct-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Granite 3.2 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-3.2-8b-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 3.2 8B Instruct · needs ~5.4 GB · from ollama.comchat in the terminal
ollama run granite3.2:8b-instruct-q4_K_M
Weights and documentation: huggingface.co/ibm-granite ↗
$ how the score was worked out · ibm-granite/granite-3.3-8b-in… 93%, Berkeley Function Calling Lea… 5%, Vectara hallucination leaderb… 1%
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 | 93% |
| Berkeley Function Calling Leaderboard result archive | 1 | 5% |
 Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 1 | 1% |
| prior · pull toward the middle | 1% | |
| weighted average | = 43.7 |
$ 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