Granite 8B Code Instruct 128k — Hardware Requirements & GPU Compatibility
ChatCode
Granite 8B Code Instruct 128k is a 8.1B-parameter open language model from IBM. It supports a context window of up to 128,000 tokens. At BF16 it needs about 16.71 GB of VRAM — see which GPUs and Macs can run it below.
1.9K downloads
25 likesSpecifications
- Publisher
- IBM
- Parameters
- 8.1B
- Architecture
- LlamaForCausalLM
- Context Length
- 128,000 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-07-27
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Granite 8B Code Instruct 128k Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 16.7 GB | 35.3 GB | 16.11 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Granite 8B Code Instruct 128k?
BF16 · 16.7 GBGranite 8B Code Instruct 128k (BF16) requires 16.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. Using the full 128K context window can add up to 18.6 GB, bringing total usage to 35.3 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Granite 8B Code Instruct 128k?
BF16 · 16.7 GB21 devices with unified memory can run Granite 8B Code Instruct 128k, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Granite 8B Code Instruct 128k need?
Granite 8B Code Instruct 128k requires 16.7 GB of VRAM at BF16. Full 128K context adds up to 18.6 GB (35.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.1B × 16 bits ÷ 8 = 16.1 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 19.2 GB (at full 128K context)
VRAM usage by quantization
BF1616.7 GBBF16 + full context35.3 GB- Can I run Granite 8B Code Instruct 128k on a Mac?
Granite 8B Code Instruct 128k requires at least 16.7 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Granite 8B Code Instruct 128k locally?
Yes — Granite 8B Code Instruct 128k can run locally on consumer hardware. At BF16 quantization it needs 16.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Granite 8B Code Instruct 128k?
At BF16, Granite 8B Code Instruct 128k can reach ~174 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~39 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 16.7 × 0.55 = ~174 tok/s
Estimated speed at BF16 (16.7 GB)
~174 tok/s~39 tok/s~130 tok/s~108 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Granite 8B Code Instruct 128k?
At BF16, the download is about 16.11 GB.
- Which GPUs can run Granite 8B Code Instruct 128k?
6 consumer GPUs can run Granite 8B Code Instruct 128k at BF16 (16.7 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Granite 8B Code Instruct 128k?
21 devices with unified memory can run Granite 8B Code Instruct 128k at BF16 (16.7 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.