Typhoon Ocr 3B — Hardware Requirements & GPU Compatibility
VisionTyphoon 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.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 125K)Best on 24 GB (Q4_K_M · ~249 tok/s · 125K)Macs from 8 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 run hf.co/mradermacher/typhoon-ocr-3b-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 20.8 GB free · 16K context
Download: typhoon-ocr-3b.Q4_K_M.gguf1.93 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun 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
Runs on RTX 3060 12GB (8 GB headroom) · Q4_K_M
- Generation speed
- ~89 tok/s
- generation speed
- Cost per 1M output tokens
- $0.20
- per 1M output tokens
How Much VRAM Does Typhoon Ocr 3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.0 GB | 3.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 125K context · ~333 tok/s | |
| 2.0 GB | 3.2 GB | 3-bit small — 3-bit small quantization | Fits: 125K context · ~324 tok/s | |
| 2.2 GB | 3.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 125K context · ~297 tok/s | |
| 2.3 GB | 3.4 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 125K context · ~291 tok/s | |
| 2.6 GB | 3.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 125K context · ~249 tok/s | |
| 3.0 GB | 4.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 125K context · ~215 tok/s | |
| 3.5 GB | 4.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 125K context · ~189 tok/s | |
| 4.1 GB | 5.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 125K context · ~159 tok/s |
Selected Q4_K_M
4-bit medium quantization3.2GBat 16K context
- Weights
- 2.3 GB
- KV cache
- 0.6 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Typhoon Ocr 3B?
Q4_K_M · 2.6 GBTyphoon 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).
≤ 11 GB
≤ 11 GB tier →fits · 0.8 GB free · up to 32K ctx
68 GPUs · 1 Mac class · 3 device families
RTX 3080~188Simulate output on RTX 3080RTX 2080 Ti~152Simulate output on RTX 2080 TiRTX 3070 Ti~150Simulate output on RTX 3070 TiM3*8 GB~27Simulate output on iMac 24" M3 (8 GB)Orin Nano~25Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~18Simulate output on iPhone 1720 GB
fits · 16.8 GB free · up to 125K ctx
1 GPU
RX 7900 XT~183Simulate output on RX 7900 XT32–40 GB
fits · 28.8 GB free · up to 125K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~443Simulate output on RTX 5090M5 Max*36 GB~122Simulate output on Mac Studio M5 Max (36 GB)M632 GB~45Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~74Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~51Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| NVIDIA Nemotron Labs Dory1.0 4B BF16NVIDIA | — | 5.7 GB | ~214 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 4B Instruct 2507Alibaba | — | 4.2 GB | ~226 | same size |
| Phi 4 Mini ReasoningMicrosoft | — | 4.8 GB | ~228 | same size |
| Qwen2.5 VL 3B InstructAlibaba | — | 3.2 GB | ~249 | same size |
| Phi 3 Mini 4k InstructMicrosoft | — | 4.2 GB | ~193 | same 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
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
★ Recommended — best balance of quality and VRAM usage.
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)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
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.