FitMyLLM
IBM/Mixture of Experts

IBMgranite-4.0-h-tiny 6.9B

📣 Update [10-07-2025]: Added a default system prompt to the chat template to guide the model towards more professional, accurate, and safe responses.

chat
6.9B
Parameters (1.5B active)
128K
Context length
9
Benchmarks
6
Quantizations
28K
HF downloads
Architecture
MoE
Released
2025-10-02
Layers
40
KV Heads
4
Head Dim
128
Family
granite

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
5.6 GB
4.7 + 0.9 KV
good
Q5_K_S5.57
6.2 GB
5.3 + 0.9 KV
good
Q5_K_M5.7
6.3 GB
5.4 + 0.9 KV
good
Q6_K6.56
7.1 GB
6.1 + 0.9 KV
excellent
Q8_08.5
8.8 GB
7.8 + 0.9 KV
lossless
FP1616
15.2 GB
14.3 + 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-4.0-H-TINY 6.9B 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)

HumanEval83.0
IFEval81.4
MBPP80.0
BBH66.3
GPQA32.6
alpacaeval30.6
MMLU-PRO27.9
MATH23.8
MUSR16.8

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run granite:6b

Tag may need adjustment — check ollama.com/library/granite for available tags.

▸ 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
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla K20c
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla K20m
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla K20s
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA GeForce GTX 1060 5 GB
5 GB VRAM • 160 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA P102-100
5 GB VRAM • 440 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Quadro P2000
5 GB VRAM • 140.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Quadro P2200
5 GB VRAM • 200.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA RTX 3050 6GB
6 GB VRAM • 168 GB/s
NVIDIA
$169
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
Intel Arc A380
6 GB VRAM • 186 GB/s
INTEL
$129
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA RTX 2060 6GB
6 GB VRAM • 336 GB/s
NVIDIA
$150
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GTX 1660 SUPER
6 GB VRAM • 336 GB/s
NVIDIA
$150
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GTX 1660 Ti
6 GB VRAM • 288 GB/s
NVIDIA
$140
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GTX 1060 6GB
6 GB VRAM • 192 GB/s
NVIDIA
$80
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA GeForce GTX 1060 6 GB
6 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 1660
6 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai

Find the best GPU for granite-4.0-h-tiny 6.9B

Build Hardware for granite-4.0-h-tiny 6.9B
▸ SPEC SHEET

granite-4.0-h-tiny 6.9B — 6.9B MoE.

▸ SPECIFICATIONS
PARAMETERS
6.9B (1.5B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
128K tokens
CAPABILITIES
chat
RELEASE DATE
2025-10-02
PROVIDER
IBM
FAMILY
granite
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.894.7 GB94%
Q5_K_S5.575.3 GB96%
Q5_K_M5.75.4 GB96%
Q6_K6.566.1 GB97%
Q8_08.57.8 GB100%
FP161614.3 GB100%
§ 01BENCHMARK SCORES
HumanEval83.0
MMLU-PRO27.9
MATH23.8
IFEval81.4
BBH66.3
GPQA32.6
MUSR16.8
MBPP80.0
alpacaeval30.6
§ 02RUN COMMAND

Run granite-4.0-h-tiny 6.9B locally with Ollama — needs 4.7 GB VRAM at Q4_K_M:

$ollama run granite:6b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA Tesla K20c
5 GB · 208 GB/s
NVIDIA Tesla K20m
5 GB · 208 GB/s
NVIDIA Tesla K20s
5 GB · 208 GB/s
NVIDIA GeForce GTX 1060 5 GB
5 GB · 160 GB/s
NVIDIA P102-100
5 GB · 440 GB/s
NVIDIA Quadro P2000
5 GB · 140.2 GB/s
NVIDIA Quadro P2200
5 GB · 200.2 GB/s
NVIDIA RTX 3050 6GB
6 GB · 168 GB/s
Intel Arc A380
6 GB · 186 GB/s
NVIDIA RTX 2060 6GB
6 GB · 336 GB/s
NVIDIA GTX 1660 SUPER
6 GB · 336 GB/s
NVIDIA GTX 1660 Ti
6 GB · 288 GB/s
NVIDIA GTX 1060 6GB
6 GB · 192 GB/s
NVIDIA Tesla C2070
6 GB · 143 GB/s
NVIDIA Tesla C2075
6 GB · 150 GB/s