Falcon H1 Tiny 90M Instruct — Hardware Requirements & GPU Compatibility
Chat
Falcon H1 Tiny 90M Instruct is a 91M-parameter open language model from TII UAE in the Falcon family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 0.38 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 256K)Best on 24 GB (Q4_K_M · ~1724 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~189 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Falcon H1 Tiny 90M Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve tiiuae/Falcon-H1-Tiny-90M-Instruct --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~616 tok/s
- generation speed
- Cost per 1M output tokens
- $0.037
- per 1M output tokens
How Much VRAM Does Falcon H1 Tiny 90M Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.4 GB | 0.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~1820 tok/s | |
| 0.4 GB | 0.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~1771 tok/s | |
| 0.4 GB | 0.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~1724 tok/s | |
| 0.4 GB | 0.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~1680 tok/s | |
| 0.4 GB | 0.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~1638 tok/s | |
| 0.4 GB | 0.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~1560 tok/s | |
| 0.5 GB | 0.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~1285 tok/s |
Selected Q4_K_M
4-bit medium quantization0.6GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.4 GB free · ~1724 tok/s
≥50 tok/s needs ≥29 GB/s · RTX 5090 ~3065, RTX 3090 Ti ~1724
Which Hardware Can Run Falcon H1 Tiny 90M Instruct?
Q4_K_M · 0.4 GBFalcon H1 Tiny 90M Instruct (Q4_K_M) requires 0.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 262K context window can add up to 3.2 GB, bringing total usage to 3.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Falcon H1 Tiny 90M Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.4 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1301Simulate output on RTX 3080RTX 2080 Ti~1054Simulate output on RTX 2080 TiRTX 3070 Ti~1041Simulate output on RTX 3070 TiM3*8 GB~189Simulate output on iMac 24" M3 (8 GB)Orin Nano~175Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~126Simulate output on iPhone 1720 GB
fits · 19.4 GB free · up to 256K ctx
1 GPU
RX 7900 XT~1263Simulate output on RX 7900 XT32–40 GB
fits · 31.4 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~3065Simulate output on RTX 5090M5 Max36 GB~847Simulate output on Mac Studio M5 Max (36 GB)M532 GB~283Simulate output on MacBook Air 13" M5 (32 GB)Orin~350Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~231Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Falcon H1 Tiny 90M Instruct
Falcon family · 13 models →Similar models
2| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Pythia 70M DedupedEleutherAI | — | 0.1 GB | ~10920 | same size |
| Distilgpt2distilbert | — | 0.1 GB | ~10920 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- TII UAE
- Family
- Falcon
- Parameters
- 91M
- Architecture
- FalconH1ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 32,768
- Release Date
- 2026-01-12
- License
- Other
Frequently Asked Questions
How much VRAM does Falcon H1 Tiny 90M Instruct need?
Falcon H1 Tiny 90M Instruct requires 0.4 GB of VRAM at Q4_K_M, or 0.5 GB at BF16. Full 262K context adds up to 3.2 GB (3.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 91M × 4.8 bits ÷ 8 = 0.1 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 3.5 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Falcon H1 Tiny 90M Instruct?
For Falcon H1 Tiny 90M Instruct, Q4_K_M (0.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Falcon H1 Tiny 90M Instruct on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Falcon H1 Tiny 90M Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Falcon H1 Tiny 90M Instruct locally?
Yes — Falcon H1 Tiny 90M Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Falcon H1 Tiny 90M Instruct?
At Q4_K_M, Falcon H1 Tiny 90M Instruct can reach ~12632 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1724 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 0.38 × 0.65 = ~13684 tok/s
Estimated speed at Q4_K_M (0.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Falcon H1 Tiny 90M Instruct?
At Q4_K_M, the download is about 0.05 GB. The full-precision BF16 version is 0.18 GB. The smallest option (Q2_K) is 0.04 GB.
Which GPUs can run Falcon H1 Tiny 90M Instruct?
52 consumer GPUs can run Falcon H1 Tiny 90M Instruct at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Falcon H1 Tiny 90M Instruct?
163 devices with unified memory can run Falcon H1 Tiny 90M Instruct at Q4_K_M (0.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.