Granite Vision 4.1 4B — Hardware Requirements & GPU Compatibility
VisionFunctions
Granite Vision 4.1 4B is IBM's 4-billion-parameter vision-language model in the Granite 4.1 family, purpose-built for enterprise document understanding rather than general chat. It is tailored for reading tables, charts, and key-value data out of scanned documents and images, and is delivered as an adapter built on top of the smaller Granite-4.1-3B text model. Its small size means it runs comfortably on modest consumer hardware once quantized, without needing a high-end GPU, making it practical for local or on-premises document-processing pipelines. The model supports a 131K token context window, enough for multi-page documents. It is released under the Apache 2.0 license, allowing unrestricted commercial and research use, and was published in April 2026 as part of IBM's broader Granite 4.1 release, which also added speech, embedding, and guardrail models.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~228 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~25 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Granite Vision 4.1 4B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/ibm-granite/granite-vision-4.1-4b-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 20.0 GB free · 16K context
Download: granite-vision-4.1-4b-Q4_K_M.gguf2.10 GBibm-granite
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (8 GB headroom) · Q4_K_M
- Generation speed
- ~82 tok/s
- generation speed
- Cost per 1M output tokens
- $0.20
- per 1M output tokens
How Much VRAM Does Granite Vision 4.1 4B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.2 GB | 4.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~302 tok/s | |
| 2.4 GB | 4.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~271 tok/s | |
| 2.9 GB | 5.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~228 tok/s | |
| 3.3 GB | 5.8 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~197 tok/s | |
| 3.8 GB | 6.3 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~174 tok/s | |
| 4.5 GB | 7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~147 tok/s | |
| 8.5 GB | 11 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~77 tok/s |
Selected Q4_K_M
4-bit medium quantization4.0GBat 16K context
- Weights
- 2.4 GB
- KV cache
- 1.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.0 GB free · ~228 tok/s
≥50 tok/s needs ≥221 GB/s · RTX 5090 ~406, RTX 3090 Ti ~228
Which Hardware Can Run Granite Vision 4.1 4B?
Q4_K_M · 2.9 GBGranite Vision 4.1 4B (Q4_K_M) requires 2.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 131K context window can add up to 10.6 GB, bringing total usage to 13.4 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Granite Vision 4.1 4B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.0 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~172Simulate output on RTX 3080RTX 2080 Ti~140Simulate output on RTX 2080 TiRTX 3070 Ti~138Simulate output on RTX 3070 TiM3*8 GB~25Simulate output on iMac 24" M3 (8 GB)Orin Nano~23Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~17Simulate output on iPhone 1720 GB
fits · 16.0 GB free · up to 128K ctx
1 GPU
RX 7900 XT~167Simulate output on RX 7900 XT32–40 GB
fits · 28.0 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~406Simulate output on RTX 5090M5 Max36 GB~112Simulate output on Mac Studio M5 Max (36 GB)M532 GB~38Simulate output on MacBook Air 13" M5 (32 GB)Orin~46Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~31Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Granite Vision 4.1 4B
Granite family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Spark X2.6 4BXHToken | — | 4.3 GB | ~221 | same size |
| NVIDIA Nemotron Labs Dory1.0 4B BF16NVIDIA | — | 5.7 GB | ~214 | same size |
| Translategemma 4B ITGoogle | — | 5 GB | ~231 | same size |
| Qwen3 4B Instruct 2507Alibaba | — | 4.2 GB | ~226 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 4 Mini ReasoningMicrosoft | — | 4.8 GB | ~228 | same size |
Specifications
- Publisher
- IBM
- Family
- Granite
- Parameters
- 4.0B
- Architecture
- Granite4VisionForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 100,352
- Release Date
- 2026-04-16
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Granite Vision 4.1 4B need?
Granite Vision 4.1 4B requires 2.9 GB of VRAM at Q4_K_M, or 8.5 GB at BF16. Full 131K context adds up to 10.6 GB (13.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.0B × 4.8 bits ÷ 8 = 2.4 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 11 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for Granite Vision 4.1 4B?
For Granite Vision 4.1 4B, Q4_K_M (2.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Granite Vision 4.1 4B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Granite Vision 4.1 4B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Granite Vision 4.1 4B locally?
Yes — Granite Vision 4.1 4B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Granite Vision 4.1 4B?
At Q4_K_M, Granite Vision 4.1 4B can reach ~1673 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~228 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 ÷ 2.87 × 0.65 = ~1812 tok/s
Estimated speed at Q4_K_M (2.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Granite Vision 4.1 4B?
At Q4_K_M, the download is about 2.40 GB. The full-precision BF16 version is 7.99 GB. The smallest option (Q2_K) is 1.70 GB.
Which GPUs can run Granite Vision 4.1 4B?
52 consumer GPUs can run Granite Vision 4.1 4B 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 Granite Vision 4.1 4B?
163 devices with unified memory can run Granite Vision 4.1 4B at Q4_K_M (2.9 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.