whatmodel.sh / Granite 3.0 8B Instruct

Granite 3.0 8B Instruct

+ contribute

Granite 3.0 8B Instruct is an open-weights language model from IBM, released October 2024. Its published size is 8.17B parameters and a 4k-token context window. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'granite-3.0-8b-instruct' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'granite-3.0-8b-instruct' as 'Granite-3.0-8B-Instruct' (IBM, Apache 2.0), linking https://huggingface.co/ibm-granite/granite-3.0-8b-instruct. Maker repo ibm-granite/granite-3.0-8b-instruct @5af5629: licence tag apache-2.0. 8,170,848,256 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-10: month the maker's Hugging Face repo was created (createdAt 2024-10-02).

43.4±0.8#476 of 719 LLMsfrom 22 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Granite 3.0 8B Instruct, out of 828 with a score, then more from IBM.

#	model	score	where	RAM	released
563	Llama 3.1 8B (base) Meta	44±3	local	~6.2GB	2024-07
564	LFM2.5 1.2B Instruct Liquid AI	44±2	local	~2.2GB	2026-01
565	Granite 3.0 8B Instruct IBM	43±1	local	~6.6GB	2024-10
566	Phi-3.5-mini-instruct Microsoft	43±1	local	~3.7GB	2024-08
567	Hermes 2 Theta Llama 3 8B Nous Research	43±2	local	~6.6GB	2024-05
	more from IBM
192	Granite 4.2 30B IBM	63±1	api $0.28/M +local	~19GB	2026-08
239	Granite 4.2 8B IBM	60±1	api $0.11/M +local	~6.6GB	2026-08
276	Granite 4.2 3B IBM	57±1	api $0.052/M +local	~3.7GB	2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #319 of 458 · 16% of its score · 6 tests

Beats GLM-4.7-Flash, Qwen3-VL 8B Instruct, Qwen3-VL 4B Instruct here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, WizardLM 70B V1.0, Llama 3.2 11B Vision Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
HumanEval lab	64.6% ✎	▄·▄█·▄·▄···█ beats 7/7	easy · avg 81%	▇▇▇ 7.5%	sharp · at its level
MBPP lab	49.6% ✎	▄···▄·▄▄█··█ beats 6/7	medium · avg 64%	▇▇ 4.0%	at its level
CodeReviewQA: solution identification (hard), invariant accuracy	25.3% ✎	▃··▁▂▂▃▂█▃▄▂ beats 16/47	medium · avg 54%	▇ 1.6%	sharp · at its level · noisy
CodeReviewQA: change localisation (hard), invariant accuracy	22.7% ✎	█▂▁▁▂▂▂▃▅▅▅▇ beats 22/47	medium · avg 36%	▇ 1.4%	sharp · noisy
CodeReviewQA: automated code refinement, exact match rate	31.8% ✎	▁▁▁▁▁▁▂▂▃█▅▄ beats 26/47	hard · avg 33%	▇ 1.1%	typical
CodeReviewQA: change type recognition, invariant accuracy	55.9% ✎	▁▁▁······▃▃█ beats 8/47	easy · avg 67%	▇ 0.0%	blunt · at its level · noisy

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #320 of 393 * · 8.6% 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	difficulty	counts	why
LMArena (text)	1183.1 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 60/379	avg 1268	▇▇ 6.2%	blunt
IFEval (aggregation unspecified) lab	52.3% ✎	▄····█·▄··██ beats 6/7	easy · avg 68%	▇ 2.4%	at its level

math▁▂▃▅▆▅▄█▄▁▁▁ #324 of 398 * · 13% of its score · 2 tests

Beats Athene-70B, GPT-3.5 Turbo (0125), Qwen2-VL 7B Instruct 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.

test	result	vs the others in its run	difficulty	counts	why
MATH (subset unspecified) lab	30.9% ✎	▄···▄▄▄▄··█▄ beats 5/7	medium · avg 53%	▇▇▇ 7.5%	at its level
GSM8K lab	69.0% ✎	█▄····▄··█▄▄ beats 7/7	easy · avg 81%	▇▇ 5.5%	sharp · at its level

other tests12 not in a task · 62% of its score

test	result	vs the others in its run	difficulty	counts	why
BIG-Bench Hard lab	51.5% ✎	▃▃···▃··█··▅ beats 7/7	medium · avg 67%	▇▇▇▇▇▇ 15%	sharp · at its level
GPQA (subset unspecified) lab	33.8% ✎	▄·▄··▄··▄█·█ beats 7/7	hard · avg 39%	▇▇▇▇ 10%	sharp
WinoGrande lab	77.5% ✎	█···▄▄▄▄···█ beats 6/7	easy · avg 84%	▇▇▇ 7.7%	at its level
MMLU lab	65.8% ✎	▄····▄·▄▄█·█ beats 6/7	easy · avg 77%	▇▇▇ 6.5%	at its level
MMLU-Pro lab	34.4% ✎	▄·····█··█▄█ beats 6/7	medium · avg 47%	▇▇ 6.1%	at its level
OpenBookQA lab	46.6% ✎	▄▄··▄··▄·█▄▄ beats 7/7	medium · avg 60%	▇▇ 4.0%	at its level
ARC Challenge lab	64.2% ✎	▄····█··▄▄▄█ beats 7/7	easy · avg 78%	▇ 3.5%	sharp · at its level · noisy
HellaSwag lab	82.6% ✎	▄·▄··█▄·▄·▄▄ beats 7/7	easy · avg 87%	▇ 3.5%	at its level

4 more tests

test	result	vs the others in its run	difficulty	counts	why
BoolQ lab	88.6% ✎	▄▄····▄▄·█·█ beats 7/7	easy · avg 91%	▇ 3.5%	at its level
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy	80.6% ✎	▁▁▁▁▁▁▁▂▄█▄▃ beats 70/146	easy · avg 83%	▇ 0.9%	at its level · noisy
Social IQA lab	71.2% ✎	▃·····▃··█▃▅ beats 7/7	medium · avg 68%	▇ 0.8%	blunt · at its level
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)	93.5% ✎	▁▁▂▃▄▄█▆▃▂▂▁ beats 48/140	very easy · avg 94%	▇ 0.5%	blunt · noisy

$ 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 | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run Granite 3.0 8B Instruct · needs ~4.9 GB · from huggingface.co/lmstudio-community
chat in the terminal
llama cli -hf lmstudio-community/granite-3.0-8b-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-3.0-8b-instruct-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Granite 3.0 8B Instruct · needs ~4.9 GB · from huggingface.co/lmstudio-community
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/lmstudio-community/granite-3.0-8b-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) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Granite 3.0 8B Instruct · needs ~5.4 GB · from ollama.com
chat in the terminal
ollama run granite3-dense:8b-instruct-q4_K_M

Weights and documentation: huggingface.co/ibm-granite ↗

$ how the score was worked out · IBM Granite 3.0 Language Mode… 88%, LMArena leaderboard dataset 6%, CodeReviewQA: The Code Review… 4% and 2 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	licence
IBM Granite 3.0 Language Models technical report (GitHub) · lab-reported	15	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 88%	Apache-2.0
LMArena leaderboard dataset	1	▇▇ 6%	CC BY 4.0
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)	4	▇ 4%	CC-BY-4.0
EuroEval leaderboards (results collection), English generative leaderboard	1	▇ 1%	MIT
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)	1	▇ 0%	Apache-2.0
prior · pull toward the middle		▇ 0%
weighted average		= 43.4