FitMyLLM
TII/Dense

TIIFalcon-H1R Tiny 90M

Falcon-H1R Tiny 90M from TII: dense, 90M parameters, 256K context. Tagged for reasoning.

chatreasoning
0.09B
Parameters
256K
Context length
0
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2026-02-10
Layers
24
KV Heads
2
Head Dim
64
Family
falcon

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
0.7 GB
0.5 + 0.1 KV
good
Q5_K_S5.57
0.7 GB
0.6 + 0.1 KV
good
Q5_K_M5.7
0.7 GB
0.6 + 0.1 KV
good
Q6_K6.56
0.7 GB
0.6 + 0.1 KV
excellent
Q8_08.5
0.7 GB
0.6 + 0.1 KV
lossless
FP1616
0.8 GB
0.7 + 0.1 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 Falcon-H1R Tiny 90M now

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

Community Ratings

Loading ratings...

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# Falcon-H1R Tiny 90M is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=Falcon-H1-Tiny-R-90M+GGUF), or use the vLLM tab with the original weights.

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.

Find the best GPU for Falcon-H1R Tiny 90M

Build Hardware for Falcon-H1R Tiny 90M
Spec sheet

Falcon-H1R Tiny 90M — 0.09B Dense.

Specifications
Parameters
0.09B
Architecture
Dense Transformer
Context Length
256K tokens
Capabilities
chat, reasoning
Release Date
2026-02-10
Provider
TII
Family
falcon
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.890.5 GB94%
Q5_K_S5.570.6 GB96%
Q5_K_M5.70.6 GB96%
Q6_K6.560.6 GB97%
Q8_08.50.6 GB100%
FP16160.7 GB100%
Compatible GPUs
30 @ Q4_K_M