LLMs ·

TeleOCR

Parameters
1.4B
Architecture
Dense
Max context
125K tokens
License
apache-2.0
Released
2026-08

How to run it

Original weights · Hugging Face

Full-precision files from XingChen-AGI, for fine-tuning, vLLM, Transformers.

huggingface.co/XingChen-AGI/TeleOCR (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from XingChen-AGI. The weights themselves download from Hugging Face.

github.com/caipeng328/TeleOCR (opens in a new tab)

Official code for full document parsing; the model card points here. Formerly named NaviDC-OCR.

git clone https://github.com/caipeng328/TeleOCR

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run TeleOCR

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App Type Opens it as Systems Engine Start
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve XingChen-AGI/TeleOCR
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path XingChen-AGI/TeleOCR
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/XingChen-AGI/TeleOCR
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 0.6 GB 2.1 GB 4.9 GB All files (opens in a new tab)
Q3_K_M Low 0.7 GB 2.2 GB 5.1 GB All files (opens in a new tab)
Q4_K_M Good 0.9 GB 2.4 GB 5.2 GB All files (opens in a new tab)
Q5_K_M High 1.0 GB 2.5 GB 5.4 GB All files (opens in a new tab)
Q6_K High 1.2 GB 2.7 GB 5.5 GB All files (opens in a new tab)
Q8_0 Very high 1.5 GB 3.0 GB 5.9 GB All files (opens in a new tab)
F16 Full 2.8 GB 4.4 GB 7.2 GB Original weights (opens in a new tab)

Best hardware for TeleOCR

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q8_0.

Quality Hardware Quant Memory Speed Runs
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060NVIDIA GeForce RTX 4060 F16 4.8 GB / 8.0 GB 55.2 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Limited EditionIntel Arc B580 F16 5.0 GB / 12.0 GB 70.6 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GBNVIDIA GeForce RTX 3060 12GB F16 5.0 GB / 12.0 GB 73.0 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPERNVIDIA GeForce RTX 4070 SUPER F16 5.0 GB / 12.0 GB 102 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Apple MacBook Air (13-inch, M4, 2025)Apple M4 (16 GB) Q8_0 3.9 GB / 10.7 GB 45.5 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Apple MacBook Pro (14-inch, M4 Pro or M4 Max, 2024)Apple M4 Pro (24 GB) F16 5.7 GB / 16.1 GB 47.7 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 9070 XT OCAMD Radeon RX 9070 XT F16 5.2 GB / 16.0 GB 112 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. ASUS Dual GeForce RTX 4060 Ti OC Edition 16GB GDDR6NVIDIA GeForce RTX 4060 Ti 16GB F16 5.2 GB / 16.0 GB 58.4 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 4070 Ti SUPER F16 5.2 GB / 16.0 GB 136 tok/s Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPERNVIDIA GeForce RTX 4080 SUPER F16 5.2 GB / 16.0 GB 149 tok/s Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?