Typhoon Ocr1.5 2B — Hardware Requirements & GPU Compatibility
Vision
Typhoon OCR 1.5 2B is OpenTyphoon's 2.1-billion-parameter vision-language OCR model for English and Thai documents, built on Qwen3-VL-2B-Instruct. Compared with the first Typhoon OCR, the card says it is faster because it no longer needs embedded PDF metadata for layout, uses a single prompt instead of two, and handles handwriting, forms and image-rich pages better. It is meant to be used with its specific prompt only. At this size, it runs on lightweight hardware, including a modest consumer GPU. The context window is 262,144 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, with the card asking users to accept the OpenTyphoon terms. Published in November 2025, it replaces the larger Typhoon OCR 3B built on Qwen2.5-VL. The card recommends the Ollama build for local use, since GGUF conversions may suffer accuracy issues.
376.0K downloads
30 likesSpecifications
- 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
Get Started
HuggingFace
How Much VRAM Does Typhoon Ocr1.5 2B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.4 GB | 31.3 GB | 0.90 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.5 GB | 31.3 GB | 0.93 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.6 GB | 31.4 GB | 1.04 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 1.6 GB | 31.4 GB | 1.06 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 1.8 GB | 31.6 GB | 1.28 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.0 GB | 31.9 GB | 1.52 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 2.3 GB | 32.1 GB | 1.76 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 2.7 GB | 32.5 GB | 2.13 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs 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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Typhoon Ocr1.5 2B?
Q4_K_M · 1.8 GB59 devices with unified memory can run Typhoon Ocr1.5 2B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Typhoon Ocr1.5 2B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
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)
KV Cache + Overhead ≈ 30.3 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M1.8 GBQ4_K_M + full context31.6 GB- 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
IQ2_XXS1.1 GBIQ3_XS1.4 GBQ4_01.6 GBIQ4_NL1.7 GBQ4_K_M ★1.8 GBBF164.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Typhoon Ocr1.5 2B on a Mac?
Typhoon Ocr1.5 2B requires at least 1.1 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Typhoon Ocr1.5 2B locally?
Yes — Typhoon Ocr1.5 2B can run locally on consumer hardware. At Q4_K_M quantization it needs 1.8 GB of VRAM. 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 ÷ 1.8 × 0.65 = ~2873 tok/s
Estimated speed at Q4_K_M (1.8 GB)
~2873 tok/s~362 tok/s~2873 tok/s~2652 tok/sReal-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?
52 consumer GPUs can run Typhoon Ocr1.5 2B at Q4_K_M (1.8 GB). 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 Typhoon Ocr1.5 2B?
59 devices with unified memory can run Typhoon Ocr1.5 2B at Q4_K_M (1.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.