FitMyLLM
Allen AI/Dense

Allen AITulu 3 8B

AI2 post-training on Llama 3.1 8B. Compact instruction-following.

chatcodingreasoning
8B
Parameters
128K
Context length
6
Benchmarks
6
Quantizations
Architecture
Dense
Released
2024-11-01
Layers
32
KV Heads
8
Head Dim
128
Family
llama

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
6.9 GB
5.4 + 1.5 KV
good
Q5_K_S5.57
7.6 GB
6.1 + 1.5 KV
good
Q5_K_M5.7
7.7 GB
6.2 + 1.5 KV
good
Q6_K6.56
8.5 GB
7.0 + 1.5 KV
excellent
Q8_08.5
10.5 GB
9.0 + 1.5 KV
lossless
FP1616
18.0 GB
16.5 + 1.5 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 Tulu 3 8B now

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

Community Ratings

Loading ratings...

Benchmarks (6)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run tulu3:8b-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

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

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

Find the best GPU for Tulu 3 8B

Build Hardware for Tulu 3 8B
Spec sheet

Tulu 3 8B — 8B Dense.

Specifications
Parameters
8B
Architecture
Dense Transformer
Context Length
128K tokens
Capabilities
chat, coding, reasoning
Release Date
2024-11-01
Provider
Allen AI
Family
llama
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.895.4 GB94%
Q5_K_S5.576.1 GB96%
Q5_K_M5.76.2 GB96%
Q6_K6.567.0 GB97%
Q8_08.59.0 GB100%
FP161616.5 GB100%
Benchmark scores
MMLU-PRO33.0
MATH22.0
IFEval81.3
BBH32.0
GPQA8.1
MUSR12.5
Run command

Run Tulu 3 8B locally with Ollama — needs 5.4 GB VRAM at Q4_K_M:

$ollama run tulu3:8b
Compatible GPUs
30 @ Q4_K_M