Granite 4.2 3B — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated September 11, 2026

Model library → IBM Granite 4.2 → Granite 4.2 3B

The smallest Granite 4.2 at about 2.6 GB Q4_K_M — it fits on almost anything, including integrated graphics and a Raspberry Pi class device. Native 128K context with a documented 512K long-context extension, built-in thinking mode, and the same tool-calling and structured-JSON post-training as its larger siblings. Apache 2.0.

Granite 4.2 3B needs about 3 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters3 Billion
Context window131,072
ArchitectureDense Decoder-Only Transformer
ProviderIBM
LicenceApache 2.0
Specified atQ4_K_M
System RAM8 GB
Record updated2026-09-11

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K1.0 GB1.8 GB~244 tok/s (est.)Fits comfortably
Q3_K_M1.3 GB2.1 GB~223 tok/s (est.)Fits comfortably
Q4_K_M1.8 GB2.6 GB~192 tok/s (est.)Fits comfortably
Q5_K_M2.1 GB2.9 GB~178 tok/s (est.)Fits comfortably
Q6_K2.5 GB3.3 GB~165 tok/s (est.)Fits comfortably
Q8_03.2 GB4.0 GB~143 tok/s (est.)Fits comfortably
F166.0 GB6.8 GB~93 tok/s (est.)Fits comfortably

Want the memory numbers alone, at every quantization level and your own context length? Use the Granite 4.2 3B VRAM calculator.

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs Granite 4.2 3B is the Intel Arc B570 (10 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run Granite 4.2 3B

Install Ollama, then run:

ollama run granite4.2:3b

Weights on Hugging Face: ibm-granite/granite-4.2-3b.

Best for: edge devices, enterprise, rag, tool use.

Can I Run Granite 4.2 3B on My GPU?

Other IBM Granite 4.2 Sizes

Granite 4.2 3B — Frequently Asked Questions

How much VRAM does Granite 4.2 3B need?
About 3 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Granite 4.2 3B run on an RTX 4090 (24 GB)?
Yes. Granite 4.2 3B needs about 3 GB at Q4_K_M, inside a 24 GB card, at an estimated 192 tokens/sec.
How do I run Granite 4.2 3B locally?
Install Ollama and run `ollama run granite4.2:3b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does IBM Granite 4.2 come in?
Granite 4.2 3B (3 GB), Granite 4.2 8B (6 GB), Granite 4.2 30B (19 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All IBM Granite 4.2 models | VRAM calculator | Check your own hardware