FITMYLLM·NOVEMBER 4, 2026·OPEN METHODOLOGY · COMMUNITY BENCHMARKS

LIVE·UPDATED DAILY

Benchmarks we ran ourselves.

▸Privacy Shield

IBM/Dense

Granite 4.2 3B

Granite 4.2 3B — IBM's smallest Granite 4.2 model: dense, Apache 2.0, with built-in thinking that can be switched off or set to low effort. 128K native context, extendable to 512K.

chatcodingreasoningmultilingualmathtool_useagentic

3.66B

Parameters

128K

Context length

9

Benchmarks

6

Quantizations

34K

HF downloads

Architecture

Dense

Released

2026-08-25

Layers

40

KV Heads

8

Head Dim

64

Family

granite

Quantization Options

Context length:

Quant	Bits	VRAM @ 16K	Quality
Q4_K_M	4.89	3.7 GB 2.7 + 0.9 KV	good
Q5_K_S	5.57	4.0 GB 3.0 + 0.9 KV	good
Q5_K_M	5.7	4.0 GB 3.1 + 0.9 KV	good
Q6_K	6.56	4.4 GB 3.5 + 0.9 KV	excellent
Q8_0	8.5	5.3 GB 4.4 + 0.9 KV	lossless
FP16	16	8.7 GB 7.8 + 0.9 KV	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN GRANITE 4.2 3B NOW

Rent on Vast.ai →Or RunPod →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (9)

AIME78.3

LiveCodeBench69.7

MMLU-PRO67.8

GPQA Diamond55.9

SciCode25.3

AA Long Context24.3

Terminal-Bench 2.113.9

HLE6.6

Terminal-Bench 40.0

Run this model

▸Easiest way to get started·Beginners

curl -fsSL https://ollama.com/install.sh | sh

$ollama run granite4.2:3b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE

>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace Ollama Library GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C2050

3 GB VRAM • 144 GB/s

NVIDIA

NVIDIA Tesla M2050

3 GB VRAM • 148 GB/s

NVIDIA

NVIDIA Tesla S2050

3 GB VRAM • 148 GB/s

NVIDIA

NVIDIA GeForce GTX 670MX

3 GB VRAM • 67 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7950

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7950 Boost

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7950 Monica BIOS 1

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7950 Monica BIOS 2

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7970

3 GB VRAM • 264 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7970 GHz Edition

3 GB VRAM • 288 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7970 X2

3 GB VRAM • 264 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 770M

3 GB VRAM • 96 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 780

3 GB VRAM • 288 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 780 Rev. 2

3 GB VRAM • 288 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 780 Ti

3 GB VRAM • 337 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7950 Mac Edition

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 7990

3 GB VRAM • 288 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 8950 OEM

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 8970 OEM

3 GB VRAM • 264 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon HD 8990 OEM

3 GB VRAM • 288 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 870M

3 GB VRAM • 120 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon R9 280

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1060 3 GB

3 GB VRAM • 192 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1060 3 GB GP104

3 GB VRAM • 192 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA P106-090

3 GB VRAM • 192 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1050 3 GB

3 GB VRAM • 84 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 5300M

3 GB VRAM • 168 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 5300 OEM

3 GB VRAM • 168 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GT 555M 3 GB

3 GB VRAM • 43.2 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD FirePro S10000

3 GB VRAM • 240 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Find the best GPU for Granite 4.2 3B

Build Hardware for Granite 4.2 3B

▸ SPEC SHEET

Granite 4.2 3B — 3.66B Dense.

▸ SPECIFICATIONS

PARAMETERS: 3.66B
ARCHITECTURE: Dense Transformer
CONTEXT LENGTH: 128K tokens
CAPABILITIES: chat, coding, reasoning, multilingual, math, tool_use, agentic
RELEASE DATE: 2026-08-25
PROVIDER: IBM
FAMILY: granite

▸ VRAM REQUIREMENTS

QUANT	BPW	VRAM	QUALITY
Q4_K_M	4.89	2.7 GB	94%
Q5_K_S	5.57	3.0 GB	96%
Q5_K_M	5.7	3.1 GB	96%
Q6_K	6.56	3.5 GB	97%
Q8_0	8.5	4.4 GB	100%
FP16	16	7.8 GB	100%

§ 01BENCHMARK SCORES

MMLU-PRO67.8

GPQA Diamond55.9

LiveCodeBench69.7

AIME78.3

HLE6.6

aa_scicode25.3

aa_lcr24.3

aa_terminal_bench_v213.9

aa_terminal_bench_v40.0

§ 02RUN COMMAND

Run Granite 4.2 3B locally with Ollama — needs 2.7 GB VRAM at Q4_K_M:

$ollama run granite4.2:3b

§ 03COMPATIBLE GPUs

30 @ Q4_K_M

NVIDIA Tesla C2050

3 GB · 144 GB/s

NVIDIA Tesla M2050

3 GB · 148 GB/s

NVIDIA Tesla S2050

3 GB · 148 GB/s

NVIDIA GeForce GTX 670MX

3 GB · 67 GB/s

AMD Radeon HD 7950

3 GB · 240 GB/s

AMD Radeon HD 7950 Boost

3 GB · 240 GB/s

AMD Radeon HD 7950 Monica BIOS 1

3 GB · 240 GB/s

AMD Radeon HD 7950 Monica BIOS 2

3 GB · 240 GB/s

AMD Radeon HD 7970

3 GB · 264 GB/s

AMD Radeon HD 7970 GHz Edition

3 GB · 288 GB/s

AMD Radeon HD 7970 X2

3 GB · 264 GB/s

NVIDIA GeForce GTX 770M

3 GB · 96 GB/s

NVIDIA GeForce GTX 780

3 GB · 288 GB/s

NVIDIA GeForce GTX 780 Rev. 2

3 GB · 288 GB/s

NVIDIA GeForce GTX 780 Ti

3 GB · 337 GB/s