Granite 3.3 8B Instruct
By IBM · United States
Updated 2026-07-13
Overview
IBM's update to Granite 3.2 8B adding fill-in-the-middle code support and improved instruction following. Apache 2.0 with strong agent and tool-use behavior.
When to pick this model
- Enterprise agents needing tool use and structured output
- RAG pipelines where instruction-following reliability matters
- Internal developer tooling combining code and chat
- Drop-in upgrade from Granite 3.2 8B
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 5 GB |
| Q5_K_M | 6 GB |
| Q8_0 | 9 GB |
| FP16 (no quantization) | 16 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 3.3 8B Instruct fits an 8 GB consumer card at Q4_K_M (5 GB). Stepping up to Q8_0 nearly doubles the footprint to 9 GB, and unquantized FP16 weights take 16 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Granite 3.3 8B Instruct needs roughly 10 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 10 tokens/sec on entry-level GPUs, on the order of 30 tokens/sec on a mid-range card, and up to 80 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Granite 3.3 8B Instruct 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 3.3 8B Instruct |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Q5_K_M (6 GB used) |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Q8_0 (9 GB used) |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | FP16 (16 GB used) |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | FP16 (16 GB used) |
| 32 GB | RTX 5090 | FP16 (16 GB used) |
Which GPU should you buy to run Granite 3.3 8B Instruct?
To run Granite 3.3 8B Instruct locally at Q4, you need ~5 GB of VRAM. The best value for this is a RTX 5060 (8 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- 128k context
- Apache 2.0 license
- Strong agentic and tool-use behavior
- Fill-in-the-middle code completion added
- Better instruction following than 3.2
Limitations
- Still very enterprise-flavored
- Less versatile than Qwen 3 8B on open-ended chat
- Code quality trails dedicated coders like Qwen 2.5 Coder 7B
Typical workloads
In our catalog grid, Granite 3.3 8B Instruct is filed under Enterprise, Code FIM — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: code generation and review (pair it with an editor integration like Continue.dev or Cline).
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: Dense · 8B · IBM Granite 3.3 · improved agents and tool use
Training: Granite 3.2 evolution with improved agent/tool use and code.
A clean upgrade over Granite 3.2 8B for enterprise agents — better tool use, better code, same Apache 2.0 backbone.
Quick start
ollama run granite3.3:8bOr 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 3.3 8B Instruct need?
At the recommended Q4_K_M quantization, Granite 3.3 8B Instruct needs about 5 GB of VRAM. Q8_0 takes 9 GB, and unquantized FP16 weights take 16 GB.
Can Granite 3.3 8B Instruct run without a GPU?
Yes — with roughly 10 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 3.3 8B Instruct support?
Granite 3.3 8B Instruct supports a 125k-token context window (128,000 tokens).
Can I use Granite 3.3 8B Instruct commercially?
Yes. Granite 3.3 8B Instruct is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Granite 3.3 8B Instruct on consumer hardware?
Our compatibility engine estimates on the order of 30 tokens/sec on a mid-range GPU and up to 80 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Granite 3.3 8B Instruct should I download first?
Start with Q4_K_M (5 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 Q5_K_M.