Falcon-H1 Tiny 90M Instruct on Annapurna Labs Alpine AL524 NAS (16 GB)

Can the Annapurna Labs Alpine AL524 NAS (16 GB) run Falcon-H1 Tiny 90M Instruct?

Yes, it runs great

Runs great. At Q6_K it needs about 1.7 GB of 12.0 GB usable, with an estimated speed of 42.1 tok/s.

Best quant: Q6_K
Generation speed: 42.1 tok/s
Prompt processing: 139 tok/s
First token (1K prompt): 7.4 s
Largest safe context: 256K

Best app to run it on the Annapurna Labs Alpine AL524 NAS (16 GB)

On Linux on ARM boards

llama.cpp

Command line + local API · runs on llama.cpp

Usually the first to support new model architectures.

llama-server -hf tiiuae/Falcon-H1-Tiny-90M-Instruct-GGUF:Q6_K

Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download Falcon-H1 Tiny 90M Instruct

Recommended for the Annapurna Labs Alpine AL524 NAS (16 GB): Q6_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q6_K file (opens in a new tab)

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:Q6_K

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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 2Basic quality (D) · 2 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the Annapurna Labs Alpine AL524 NAS (16 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	1.3 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	3.3 / 15
Match score	44.7 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Annapurna Labs Alpine AL524 NAS (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	1.7 GB	12.0 GB	99.6 tok/s	Runs great	2Basic quality (D) · 2 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	1.7 GB	12.0 GB	78.4 tok/s	Runs great	2Basic quality (D) · 2 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	1.7 GB	12.0 GB	60.6 tok/s	Runs great	2Basic quality (D) · 2 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	1.7 GB	12.0 GB	50.1 tok/s	Runs great	2Basic quality (D) · 2 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	1.7 GB	12.0 GB	42.1 tok/s	Runs great	2Basic quality (D) · 2 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	1.8 GB	12.0 GB	30.9 tok/s	Runs great	3Basic quality (D) · 3 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	1.8 GB	12.0 GB	14.2 tok/s	Runs well	3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 (16 GB) F16 · 188 tok/s · Runs great
3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 (16 GB) F16 · 331 tok/s · Runs great
3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 870 tok/s · Runs great
3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 (24 GB) F16 · 331 tok/s · Runs great
3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) F16 · 752 tok/s · Runs great
3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 1,115 tok/s · Runs great

Quick answers

How much memory does Falcon-H1 Tiny 90M Instruct need on the Annapurna Labs Alpine AL524 NAS 16GB?

At Q6_K it needs about 1.7 GB. The Annapurna Labs Alpine AL524 NAS 16GB has 12.0 GB usable.

How fast is Falcon-H1 Tiny 90M Instruct on the Annapurna Labs Alpine AL524 NAS 16GB?

About 42.1 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Falcon-H1 Tiny 90M Instruct should I use on the Annapurna Labs Alpine AL524 NAS 16GB?

Q6_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.