Can the NVIDIA Quadro RTX 8000 run TeleOCR?

Yes, it runs great

Runs great. At F16 it needs about 6.8 GB of 48.0 GB usable, with an estimated speed of 136 tok/s.

Best quant: F16
Generation speed: 136 tok/s
Prompt processing: 8,265 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 125K

Best app to run it on the NVIDIA Quadro RTX 8000

On Windows

Inference server · runs on 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.
On Windows it runs through WSL2.

vllm serve XingChen-AGI/TeleOCR

SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
Docker Model Runner Handy if you already work in Docker.

On Linux

vLLM

Inference server · runs on 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.

vllm serve XingChen-AGI/TeleOCR

SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
Docker Model Runner Handy if you already work in Docker.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download TeleOCR

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 6 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA Quadro RTX 8000: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	18.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	3.3 / 15
Match score	61.3 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA Quadro RTX 8000

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	4.5 GB	48.0 GB	954 tok/s	Runs great	28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	4.6 GB	48.0 GB	751 tok/s	Runs great	33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	4.8 GB	48.0 GB	581 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	4.9 GB	48.0 GB	480 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	5.1 GB	48.0 GB	403 tok/s	Runs great	39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	5.4 GB	48.0 GB	296 tok/s	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	6.8 GB	48.0 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 61/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

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 4060 F16 · 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 F16 · 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 12GB F16 · 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 SUPER F16 · 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 M4 (16 GB) Q8_0 · 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 M4 Pro (24 GB) F16 · 47.7 tok/s · Runs great

Quick answers

How much memory does TeleOCR need on the NVIDIA Quadro RTX 8000 48GB?

At F16 it needs about 6.8 GB. The NVIDIA Quadro RTX 8000 48GB has 48.0 GB usable.

How fast is TeleOCR on the NVIDIA Quadro RTX 8000 48GB?

About 136 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of TeleOCR should I use on the NVIDIA Quadro RTX 8000 48GB?

F16. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.