Typhoon Ocr1.5 2B — Hardware Requirements & GPU Compatibility
VisionFunctionsTyphoon OCR 1.5 2B serves as OpenTyphoon's 2.1-billion-parameter vision-language model designed for English and Thai documents, built on Qwen3-VL-2B-Instruct. Compared to the earlier Typhoon OCR, this version is faster because it skips embedded PDF metadata for layout analysis, relies on a single prompt rather than two, and manages handwriting, forms, and image-heavy pages more effectively. It is intended for use with its specific prompt only. Given its size, it runs smoothly on lightweight hardware, including modest consumer GPUs. The context window supports 262,144 tokens. Released under the Apache 2.0 license, it allows unrestricted commercial and research usage, though users must accept OpenTyphoon terms per the card's request. Published in November 2025, it takes the place of the larger Typhoon OCR 3B built on Qwen2.5-VL. The card suggests using the Ollama build for local setups, since GGUF conversions might face accuracy problems.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~362 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~40 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Typhoon Ocr1.5 2B
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-ocr1.5-2b-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 20.5 GB free · 16K context
Download: typhoon-ocr1.5-2b.Q4_K_M.gguf1.11 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
- ~129 tok/s
- generation speed
- Cost per 1M output tokens
- $0.14
- per 1M output tokens
How Much VRAM Does Typhoon Ocr1.5 2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.4 GB | 5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~455 tok/s | |
| 1.5 GB | 5 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~446 tok/s | |
| 1.6 GB | 5.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~417 tok/s | |
| 1.6 GB | 5.1 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~410 tok/s | |
| 1.8 GB | 5.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~362 tok/s | |
| 2.0 GB | 5.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~320 tok/s | |
| 2.3 GB | 5.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~286 tok/s | |
| 2.7 GB | 6.2 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~246 tok/s |
Selected Q4_K_M
4-bit medium quantization3.5GBat 16K context
- Weights
- 1.3 GB
- KV cache
- 1.9 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Typhoon Ocr1.5 2B?
Q4_K_M · 1.8 GBTyphoon Ocr1.5 2B (Q4_K_M) requires 1.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 262K context window can add up to 29.8 GB, bringing total usage to 31.6 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Typhoon Ocr1.5 2B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).
≤ 11 GB
≤ 11 GB tier →fits · 0.6 GB free · up to 16K ctx
68 GPUs · 1 Mac class · 3 device families
RTX 3080~273Simulate output on RTX 3080RTX 2080 Ti~221Simulate output on RTX 2080 TiRTX 3070 Ti~219Simulate output on RTX 3070 TiM3*8 GB~40Simulate output on iMac 24" M3 (8 GB)Orin Nano~37Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~26Simulate output on iPhone 1720 GB
fits · 16.6 GB free · up to 128K ctx
1 GPU
RX 7900 XT~265Simulate output on RX 7900 XT32–40 GB
fits · 28.6 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~644Simulate output on RTX 5090M5 Max*36 GB~178Simulate output on Mac Studio M5 Max (36 GB)M632 GB~66Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~108Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~74Simulate 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 |
|---|---|---|---|---|
| LFM3 Omni 2BLiquid AI | — | 2.4 GB | ~385 | same size |
| Hy MT2 1.8BTencent | — | 2.6 GB | ~395 | same size |
| Qwen3.5 2BAlibaba | — | 1.9 GB | ~370 | same size |
| Qwen3 VL 2B InstructAlibaba | — | 3.5 GB | ~362 | same size |
| Qwen2 VL 2B InstructAlibaba | — | 2.1 GB | ~390 | same size |
| Kimi K3 DSparkRadixArk | — | 2.2 GB | ~381 | same size |
Specifications
- Publisher
- typhoon-ai
- Parameters
- 2.1B
- Architecture
- Qwen3VLForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-11-10
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Typhoon Ocr1.5 2B need?
Typhoon Ocr1.5 2B requires 1.8 GB of VRAM at Q4_K_M, or 4.8 GB at BF16. Full 262K context adds up to 29.8 GB (31.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.1B × 4.8 bits ÷ 8 = 1.3 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 ≈ 30.3 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Typhoon Ocr1.5 2B?
For Typhoon Ocr1.5 2B, Q4_K_M (1.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Typhoon Ocr1.5 2B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Typhoon Ocr1.5 2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Typhoon Ocr1.5 2B locally?
Yes — Typhoon Ocr1.5 2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Typhoon Ocr1.5 2B?
At Q4_K_M, Typhoon Ocr1.5 2B can reach ~2652 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~362 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 ÷ 1.81 × 0.65 = ~2873 tok/s
Estimated speed at Q4_K_M (1.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Typhoon Ocr1.5 2B?
At Q4_K_M, the download is about 1.28 GB. The full-precision BF16 version is 4.26 GB. The smallest option (IQ2_XXS) is 0.59 GB.
Which GPUs can run Typhoon Ocr1.5 2B?
114 consumer GPUs can run Typhoon Ocr1.5 2B 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 Ocr1.5 2B?
185 devices with unified memory can run Typhoon Ocr1.5 2B at Q4_K_M (1.8 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.