Granite 4.1 8B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
Dense 8B model reported to match IBM's prior 32B MoE flagship on several benchmarks. Q4 fits in ~5GB — runs on any modern GPU or Apple Silicon. Apache 2.0, 128K context.
Granite 4.1 8B needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 3.4 GB | ~154 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 4.2 GB | ~133 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 5.6 GB | ~107 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 6.5 GB | ~95 tok/s | Fits | |
| Q6_K 6.56 bpw | 7.4 GB | ~86 tok/s | Fits | |
| Q8_0 8.50 bpw | 9.3 GB | ~70 tok/s | Fits | |
| F16 16.00 bpw | 16.8 GB | ~41 tok/s | Fits |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Granite 4.1 8B VRAM calculator →
Get Granite 4.1 8B running
The cheapest catalogued GPU that runs Granite 4.1 8B is the Intel Arc B570 (10 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Granite 4.1 8B
Install Ollama, then run:
ollama run granite4.1:8bSpecifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 8 Billion
- Context window
- 128,000
- Architecture
- Dense Transformer
- Provider
- IBM
- Licence
- Apache 2.0
- Practical deployment
- Laptop
- Specified at
- Q4_K_M
- System RAM
- 16 GB
- Record updated
- 2026-04-29
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run Granite 4.1 8B on my GPU?
- Granite 4.1 8B on AMD Radeon RX 9060 XT 8GB
- Granite 4.1 8B on Apple M1 Max
- Granite 4.1 8B on Apple M3 Max
- Granite 4.1 8B on Apple M5 Pro
- Granite 4.1 8B on Intel Arc B570
- Granite 4.1 8B on Intel Arc B580
- Granite 4.1 8B on NVIDIA GeForce RTX 3060 (12GB)
- Granite 4.1 8B on NVIDIA GeForce RTX 3070
- Granite 4.1 8B on NVIDIA GeForce RTX 3070 Ti
- Granite 4.1 8B on NVIDIA GeForce RTX 3080 (10GB)
- Granite 4.1 8B on NVIDIA GeForce RTX 4060
- Granite 4.1 8B on NVIDIA GeForce RTX 4070
- Granite 4.1 8B on NVIDIA GeForce RTX 4070 Super
- Granite 4.1 8B on NVIDIA GeForce RTX 4070 Ti
- Granite 4.1 8B on NVIDIA GeForce RTX 5060
- Granite 4.1 8B on NVIDIA GeForce RTX 5060 Ti 8GB
- Granite 4.1 8B on NVIDIA GeForce RTX 5070
- Granite 4.1 8B on NVIDIA L40S
- Granite 4.1 8B on NVIDIA RTX 6000 Ada Generation
Other IBM Granite 4.1 sizes
Granite 4.1 8B — frequently asked questions
How much VRAM does Granite 4.1 8B need?
About 6 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Granite 4.1 8B run on an RTX 4090 (24 GB)?
Yes. Granite 4.1 8B needs about 6 GB at Q4_K_M, inside a 24 GB card, at an estimated 107 tokens/sec.
How do I run Granite 4.1 8B locally?
Install Ollama and run `ollama run granite4.1:8b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does IBM Granite 4.1 come in?
Granite 4.1 3B (3 GB), Granite 4.1 8B (6 GB), Granite 4.1 30B (19 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.