IB
IBM
Language model · United States ·Dec 2024

Granite 3.1 8B

Language Open (Restricted)
8.1B
Parameters
10
Benchmarks

About Granite 3.1 8B

Granite 3.1 8B is an AI model developed by IBM, in the language category, released in 2024, made available as an open-weights model with 8.1B params.

On this page you'll find Granite 3.1 8B's full specifications, including 10 benchmark results. Review provider pricing and benchmark scores below, or compare Granite 3.1 8B head-to-head with other language models.

→ More models by IBM → All language models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run Granite 3.1 8B locally — what to buy

Share this build ↗

Sized to what Granite 3.1 8B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
Intel Arc B580 12GB
Consumer GPU · ~$249
~72.4 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Intel Arc A770 16GB
Consumer GPU · ~$329
~88.9 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5070
Consumer GPU · ~$549
~120 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
35.6–120+ tok/s
32 options →
Apple
21.5–120+ tok/s
18 options →
Datacenter GPU
120+ tok/s
13 options →

Community

Would you run Granite 3.1 8B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Granite 3.1 8B benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
HumanEval code 89.63% instruct-cited-granite-3-2
HumanEval+ code 85.79% instruct-cited-granite-3-2
AlpacaEval 2 general 30.34% instruct-cited-granite-3-2
ArenaHard general 37.58% instruct-cited-granite-3-2
IFEval general 73.2% instruct-cited-granite-3-2
MMLU general 66.77% instruct-cited-granite-3-2
GSM8K math 79.15% instruct-cited-granite-3-2
BIG-Bench Hard reasoning 68.55% instruct-cited-granite-3-2
DROP reasoning 50.78% instruct-cited-granite-3-2
TruthfulQA safety 65.84% instruct-cited-granite-3-2

More models like Granite 3.1 8B

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is Granite 3.1 8B? ▶

Granite 3.1 8B is an AI model developed by IBM, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Granite 3.1 8B? ▶

Granite 3.1 8B was developed by IBM and released in 2024.

Is Granite 3.1 8B open source or proprietary? ▶

Granite 3.1 8B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Granite 3.1 8B cost? ▶

Pricing for Granite 3.1 8B depends on the provider. See the providers table on this page for the latest API rates.

How does Granite 3.1 8B perform on benchmarks? ▶

Granite 3.1 8B is benchmarked across 10 evaluations on GenAIList, including HumanEval (89.63%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about Granite 3.1 8B?