llmrun
IBMGraniteIdefics3ForConditionalGeneration

Granite Docling 258M — Hardware Requirements & GPU Compatibility

VisionChatCodeMath

Granite Docling 258M is IBM Research's multimodal model with 258 million parameters, designed for document conversion. Built on Idefics3 architecture, it uses a siglip2-base-patch16-512 vision encoder and a Granite 165M language model. The system converts page images into structured DoclingDocument output and integrates with the Docling library; it is not a chat model. Compared to SmolDocling-256M-preview, the card notes better equation recognition, flexible inference for full pages or specific regions, improved stability against infinite loops, document element question answering, plus experimental support for Japanese, Arabic and Chinese. At this size, it runs on a modest consumer GPU or CPU. Context length reaches 8,192 tokens. Released under the Apache 2.0 license, it allows unrestricted commercial and research use. The Hub repository dates from May 2025, while the card lists a release date of September 17, 2025. As the successor to SmolDocling preview, this model is intended for Docling pipelines.

258M params · dense8K contextApache 2.0245.9K downloads1.3K likes4.0K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 8KBest on24 GB Q4_K_M · ~1310 tok/s · 8KMacs from8 GB Q4_K_M · ~143 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Granite Docling 258M

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
one command · needs Ollama installed
$ollama run hf.co/gguf-org/docling-gguf:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 23.4 GB free · 8K context

Download: docling-q4_k_m.gguf0.48 GBgguf-org

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

  • The easiest way to try this model
  • Running in a few minutes, easy setup
  • Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does Granite Docling 258M Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
0.5 GB—3-bit · i-quant medium — Importance-weighted 3-bit, mediumFits: 8K context · ~1424 tok/s
0.5 GB—2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 8K context · ~1424 tok/s
0.5 GB—3-bit medium — 3-bit medium quantizationFits: 8K context · ~1394 tok/s
0.5 GB—4-bit · legacy — 4-bit legacy quantizationFits: 8K context · ~1365 tok/s
0.5 GB—4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 8K context · ~1310 tok/s
0.5 GB—5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 8K context · ~1236 tok/s
0.6 GB—6-bit, very good — 6-bit quantization, very good qualityFits: 8K context · ~1170 tok/s
0.6 GB—8-bit, near-lossless — 8-bit quantization, near-losslessFits: 8K context · ~1092 tok/s

Selected Q4_K_M

4-bit medium quantization

0.6GBat 8K context

Weights
0.2 GB
KV cache
0.2 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 23.4 GB free · ~1310 tok/s

≥50 tok/s needs ≥38 GB/s · RTX 5090 ~2330, M5 Ultra ~1719

Which Hardware Can Run Granite Docling 258M?

Q4_K_M · 0.5 GB

Granite Docling 258M (Q4_K_M) requires 0.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 8K context window can add up to 0.1 GB, bringing total usage to 0.6 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Granite Docling 258M, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 0.6 GB · ~354 tok/s · 8K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 0.6 GB · ~468 tok/s · 8K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 0.6 GB · ~582 tok/s · 8K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 0.6 GB · ~1310 tok/s · 8K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 0.6 GB · ~168 tok/s · 8KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 0.6 GB · ~764 tok/s · 8KMacs →

Alternatives to Granite Docling 258M

Granite family · 28 models →

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Gemma 3 270M ITGoogle—1.2 GB~3640same size
SmolVLM2 256M Video InstructHugging Face—0.6 GB~1310same size
SmolVLM 256M InstructHugging Face—0.6 GB~1310same size
Functiongemma 270M ITGoogle—1.6 GB~1111same size
Tiny MixtralTitanML—0.5 GB~2329same size
Vlt5 Base KeywordsVoicelab—1.6 GB~1074same size

Specifications

Publisher
IBM
Family
Granite
Parameters
258M
Architecture
Idefics3ForConditionalGeneration
Context Length
8,192 tokens
Vocabulary Size
100,352
Release Date
2025-05-19
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Granite Docling 258M need?

Granite Docling 258M requires 0.5 GB of VRAM at Q4_K_M, or 0.9 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 258M × 4.8 bits ÷ 8 = 0.2 GB

KV Cache + Overhead ≈ 0.3 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 ≈ 0.4 GB (at full 8K context)

VRAM usage by quantization

0.5 GB
0.6 GB

Learn more about VRAM estimation →

What's the best quantization for Granite Docling 258M?

For Granite Docling 258M, Q4_K_M (0.5 GB) offers the best balance of quality and VRAM usage. Q5_0 (0.5 GB) provides better quality if you have the VRAM. The smallest option is IQ3_M at 0.5 GB.

VRAM requirement by quantization

IQ3_M
0.5 GB
Q4_0
0.5 GB
Q4_K_M ★
0.5 GB
Q5_0
0.5 GB
Q5_K_M
0.5 GB
BF16
0.9 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Granite Docling 258M on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Granite Docling 258M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.5 GB of usable unified memory (RAM minus macOS overhead).

Can I run Granite Docling 258M locally?

Yes — Granite Docling 258M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Granite Docling 258M?

At Q4_K_M, Granite Docling 258M can reach ~9600 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1310 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 ÷ 0.5 × 0.65 = ~10400 tok/s

Estimated speed at Q4_K_M (0.5 GB)

~10400 tok/s
~1310 tok/s
~10400 tok/s
~9600 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Granite Docling 258M?

At Q4_K_M, the download is about 0.15 GB. The full-precision BF16 version is 0.52 GB. The smallest option (IQ3_M) is 0.12 GB.

Which GPUs can run Granite Docling 258M?

114 consumer GPUs can run Granite Docling 258M at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB. 114 GPUs have plenty of headroom for comfortable inference.

Which devices can run Granite Docling 258M?

185 devices with unified memory can run Granite Docling 258M at Q4_K_M (0.5 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.