Granite 4.0 H-Tiny 7B-A1B

Overview

IBM's edge-class hybrid MoE with 7B total and only 1B active parameters — Apache 2.0 licensed and built for embedded and low-cost serving.

When to pick this model

• On-device assistants on laptops or edge boxes
• High-QPS endpoints where active-param cost dominates
• Long-context summarization on memory-constrained hardware
• Embedded products needing a clean commercial license
• Prototyping pipelines before scaling to Granite 4.0 Small

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	4 GB
Q5_K_M	5 GB
Q8_0	7 GB
FP16 (no quantization)	14 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, Granite 4.0 H-Tiny 7B-A1B fits an 8 GB consumer card at Q4_K_M (4 GB). Stepping up to Q8_0 nearly doubles the footprint to 7 GB, and unquantized FP16 weights take 14 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, Granite 4.0 H-Tiny 7B-A1B needs roughly 8 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 60 tokens/sec on entry-level GPUs, on the order of 180 tokens/sec on a mid-range card, and up to 350 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches Granite 4.0 H-Tiny 7B-A1B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memory	Example cards	Best fit for Granite 4.0 H-Tiny 7B-A1B
8 GB	RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB	Q8_0 (7 GB used)
12 GB	RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop	Q8_0 (7 GB used)
16 GB	RTX 5080, RTX 4080 Super, Radeon RX 9070 XT	FP16 (14 GB used)
24 GB	RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop	FP16 (14 GB used)
32 GB	RTX 5090	FP16 (14 GB used)

Which GPU should you buy to run Granite 4.0 H-Tiny 7B-A1B?

To run Granite 4.0 H-Tiny 7B-A1B locally at Q4, you need ~4 GB of VRAM. The best value for this is a RTX 5060 (8 GB VRAM).

Strengths

• Extremely low compute cost per token via 1B active params
• Apache 2.0 license with no commercial strings attached
• 128k context handled efficiently thanks to hybrid Mamba-2
• Tiny memory footprint suits edge and serverless deploys

Limitations

• Quality lags dense 3B models on some single-shot tasks
• Smaller active capacity hurts complex reasoning
• Needs current llama.cpp support to run efficiently

Typical workloads

In our catalog grid, Granite 4.0 H-Tiny 7B-A1B is filed under Edge, Fast On-device — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: everyday chat, drafting and summarization.

The 125k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.

Architecture & training

Architecture: Hybrid Mamba-2 + granular MoE · 7B/1B active

Training: Edge variant of 4.0.

Quick start

ollama run granite4:tiny-h

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does Granite 4.0 H-Tiny 7B-A1B need?

At the recommended Q4_K_M quantization, Granite 4.0 H-Tiny 7B-A1B needs about 4 GB of VRAM. Q8_0 takes 7 GB, and unquantized FP16 weights take 14 GB.

Can Granite 4.0 H-Tiny 7B-A1B run without a GPU?

Yes — with roughly 8 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does Granite 4.0 H-Tiny 7B-A1B support?

Granite 4.0 H-Tiny 7B-A1B supports a 125k-token context window (128,000 tokens).

Can I use Granite 4.0 H-Tiny 7B-A1B commercially?

Yes. Granite 4.0 H-Tiny 7B-A1B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.

How fast is Granite 4.0 H-Tiny 7B-A1B on consumer hardware?

Our compatibility engine estimates on the order of 180 tokens/sec on a mid-range GPU and up to 350 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of Granite 4.0 H-Tiny 7B-A1B should I download first?

Start with Q4_K_M (4 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It already fits an 8 GB card at Q8_0.