TII/Dense

TIIFalcon-H1 1.5B

Small hybrid model. Fast inference with 256K context.

chatcoding
1.5B
Parameters
128K
Context length
10
Benchmarks
6
Quantizations
Architecture
Dense
Released
2025-08-01
Layers
28
KV Heads
8
Head Dim
96
Family
falcon

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.891.4 GBgood
Q5_K_S5.571.5 GBgood
Q5_K_M5.71.6 GBgood
Q6_K6.561.7 GBexcellent
Q8_08.52.1 GBlossless
FP16163.5 GBlossless

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

READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN FALCON-H1 1.5B NOW

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

Community Ratings

Loading ratings...

Benchmarks (10)

IFEval80.7
MATH74.0
HumanEval68.3
MBPP64.8
BBH46.5
MMLU-PRO37.8
GPQA Diamond35.2
LiveCodeBench17.6
MUSR10.6
GPQA2.2

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run falcon:2b-q4_K_M

Tag may need adjustment — check ollama.com/library/falcon 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

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla D870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla S870
2 GB VRAM • 76.8 GB/s
NVIDIA

Find the best GPU for Falcon-H1 1.5B

Build Hardware for Falcon-H1 1.5B
▸ SPEC SHEET

Falcon-H1 1.5B1.5B Dense.

▸ SPECIFICATIONS
PARAMETERS
1.5B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
128K tokens
CAPABILITIES
chat, coding
RELEASE DATE
2025-08-01
PROVIDER
TII
FAMILY
falcon
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.891.4 GB94%
Q5_K_S5.571.5 GB96%
Q5_K_M5.71.6 GB96%
Q6_K6.561.7 GB97%
Q8_08.52.1 GB100%
FP16163.5 GB100%
§ 01BENCHMARK SCORES
HumanEval68.3
MMLU-PRO37.8
MATH74.0
IFEval80.7
BBH46.5
GPQA2.2
MUSR10.6
MBPP64.8
LiveCodeBench17.6
GPQA Diamond35.2