llmrun
typhoon-aiQwen2_5_VLForConditionalGeneration

Typhoon Ocr 3B — Hardware Requirements & GPU Compatibility

Vision

Typhoon OCR 3B serves as OpenTyphoon's document parsing model with 3.8 billion parameters, designed for Thai and English text. It builds on Qwen2.5-VL-3B-Instruct, drawing inspiration from olmOCR to turn documents like financial reports, government forms, books, and receipts into Markdown—complete with HTML tables and structured figure descriptions. The project notes that it beats GPT-4o and Gemini 2.5 Flash at understanding Thai documents, provided users follow its specific prompts. Given its size, quantized versions fit on a single modest consumer GPU. The model handles up to 128,000 tokens in context. Released under the Apache 2.0 license for unrestricted commercial and research use, it still requires users to accept OpenTyphoon's terms before deployment. Published in May 2025, this model was followed by Typhoon OCR 1.5 2B, which is smaller. For local setups, the card recommends the Ollama build because GGUF files might lose some accuracy.

3.8B params · dense128K contextApache 2.054.2K downloads10 likes1.2K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 125KBest on24 GB Q4_K_M · ~249 tok/s · 125KMacs from8 GB Q4_K_M · ~27 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Typhoon Ocr 3B

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/mradermacher/typhoon-ocr-3b-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 20.8 GB free · 16K context

Download: typhoon-ocr-3b.Q4_K_M.gguf1.93 GBmradermacher

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 Typhoon Ocr 3B Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
2.0 GB3.1 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 125K context · ~333 tok/s
2.0 GB3.2 GB3-bit small — 3-bit small quantizationFits: 125K context · ~324 tok/s
2.2 GB3.3 GB3-bit medium — 3-bit medium quantizationFits: 125K context · ~297 tok/s
2.3 GB3.4 GB4-bit · legacy — 4-bit legacy quantizationFits: 125K context · ~291 tok/s
2.6 GB3.8 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 125K context · ~249 tok/s
3.0 GB4.2 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 125K context · ~215 tok/s
3.5 GB4.6 GB6-bit, very good — 6-bit quantization, very good qualityFits: 125K context · ~189 tok/s
4.1 GB5.3 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 125K context · ~159 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

3.2GBat 16K context

Weights
2.3 GB
KV cache
0.6 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 20.8 GB free · ~249 tok/s

≥50 tok/s needs ≥202 GB/s · RTX 5090 ~443, M5 Ultra ~327

Which Hardware Can Run Typhoon Ocr 3B?

Q4_K_M · 2.6 GB

Typhoon Ocr 3B (Q4_K_M) requires 2.6 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 128K context window can add up to 4.6 GB, bringing total usage to 7.3 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Typhoon Ocr 3B, 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 · 3.2 GB · ~67 tok/s · 125K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 3.2 GB · ~89 tok/s · 125K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 3.2 GB · ~111 tok/s · 125K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 3.2 GB · ~249 tok/s · 125K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 3.2 GB · ~32 tok/s · 125KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 3.2 GB · ~145 tok/s · 125KMacs →

Alternatives to Typhoon Ocr 3B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
NVIDIA Nemotron Labs Dory1.0 4B BF16NVIDIA—5.7 GB~214same size
Granite Vision 4.1 4BIBM—4 GB~228same size
Qwen3 4B Instruct 2507Alibaba—4.2 GB~226same size
Phi 4 Mini ReasoningMicrosoft—4.8 GB~228same size
Qwen2.5 VL 3B InstructAlibaba—3.2 GB~249same size
Phi 3 Mini 4k InstructMicrosoft—4.2 GB~193same size

Specifications

Publisher
typhoon-ai
Parameters
3.8B
Architecture
Qwen2_5_VLForConditionalGeneration
Context Length
128,000 tokens
Vocabulary Size
151,936
Release Date
2025-05-27
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Typhoon Ocr 3B need?

Typhoon Ocr 3B requires 2.6 GB of VRAM at Q4_K_M, or 7.9 GB at BF16. Full 128K context adds up to 4.6 GB (7.3 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 3.8B × 4.8 bits ÷ 8 = 2.3 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 ≈ 5 GB (at full 128K context)

VRAM usage by quantization

2.6 GB
7.3 GB

Learn more about VRAM estimation →

What's the best quantization for Typhoon Ocr 3B?

For Typhoon Ocr 3B, Q4_K_M (2.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (3.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.4 GB.

VRAM requirement by quantization

IQ2_XXS
1.4 GB
IQ3_XS
1.9 GB
Q4_0
2.3 GB
IQ4_NL
2.5 GB
Q4_K_M ★
2.6 GB
BF16
7.9 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Typhoon Ocr 3B on a Mac?

Yes — Mac Mini M2 (8 GB) and 158 other Macs can run Typhoon Ocr 3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.6 GB of usable unified memory (RAM minus macOS overhead).

Can I run Typhoon Ocr 3B locally?

Yes — Typhoon Ocr 3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Typhoon Ocr 3B?

At Q4_K_M, Typhoon Ocr 3B can reach ~1825 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~249 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 ÷ 2.63 × 0.65 = ~1977 tok/s

Estimated speed at Q4_K_M (2.6 GB)

~1977 tok/s
~249 tok/s
~1977 tok/s
~1825 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 Typhoon Ocr 3B?

At Q4_K_M, the download is about 2.25 GB. The full-precision BF16 version is 7.51 GB. The smallest option (IQ2_XXS) is 1.03 GB.

Which GPUs can run Typhoon Ocr 3B?

114 consumer GPUs can run Typhoon Ocr 3B 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 Typhoon Ocr 3B?

185 devices with unified memory can run Typhoon Ocr 3B at Q4_K_M (2.6 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.