Check my GPU

LLMs ·

Falcon-H1 Tiny 90M Instruct

Parameters
0.1B
Architecture
Dense
Max context
256K tokens
License
falcon-llm-license
Released
2026-01

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/tiiuae/Falcon-H1-Tiny-90M-Instruct-GGUF (opens in a new tab)

ollama run hf.co/tiiuae/Falcon-H1-Tiny-90M-Instruct-GGUF

Original weights · Hugging Face

Full-precision files from TII, for fine-tuning, vLLM, Transformers.

huggingface.co/tiiuae/Falcon-H1-Tiny-90M-Instruct (opens in a new tab)

No sign-in needed.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: parallel attention + Mamba in every layer.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 0.0 GB 0.7 GB 1.0 GB GGUF (opens in a new tab)
Q3_K_M Low 0.0 GB 0.7 GB 1.0 GB GGUF (opens in a new tab)
Q4_K_M Good 0.1 GB 0.8 GB 1.1 GB GGUF (opens in a new tab)
Q5_K_M High 0.1 GB 0.8 GB 1.1 GB GGUF (opens in a new tab)
Q6_K High 0.1 GB 0.8 GB 1.1 GB GGUF (opens in a new tab)
Q8_0 Very high 0.1 GB 0.8 GB 1.1 GB GGUF (opens in a new tab)
F16 Full 0.2 GB 0.9 GB 1.2 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Falcon-H1 Tiny 90M Instruct

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at F16.

Grade · points Hardware Quant Memory Speed Fit
45 ptsUsable (C) · 45 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 Apple M1 (16 GB) F16 1.7 GB / 10.7 GB 188 tok/s Runs well
45 ptsUsable (C) · 45 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 Apple M4 (16 GB) F16 1.7 GB / 10.7 GB 331 tok/s Runs well
45 ptsUsable (C) · 45 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 NVIDIA GeForce RTX 4060 F16 1.3 GB / 8.0 GB 870 tok/s Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15 Apple M4 (24 GB) F16 2.2 GB / 16.1 GB 331 tok/s Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15 Apple M4 Pro (24 GB) F16 2.2 GB / 16.1 GB 752 tok/s Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15 Intel Arc B580 F16 1.5 GB / 12.0 GB 1,115 tok/s Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15 NVIDIA GeForce RTX 3060 12GB F16 1.5 GB / 12.0 GB 1,152 tok/s Runs well
44 ptsUsable (C) · 44 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15 NVIDIA GeForce RTX 4070 SUPER F16 1.5 GB / 12.0 GB 1,613 tok/s Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15 AMD Radeon RX 9070 XT F16 1.7 GB / 16.0 GB 1,764 tok/s Runs well
43 ptsUsable (C) · 43 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15 NVIDIA GeForce RTX 4060 Ti 16GB F16 1.7 GB / 16.0 GB 922 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.