Can the NVIDIA L4 run Chandra OCR 2?

Yes, it runs great

Runs great. At Q6_K it needs about 6.4 GB of 24.0 GB usable, with an estimated speed of 48.2 tok/s.

Best quant: Q6_K
Generation speed: 48.2 tok/s
Prompt processing: 4,116 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Best app to run it on the NVIDIA L4

On Linux

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 datalab-to/chandra-ocr-2

LM Studio Point-and-click: search, download and chat in one window.
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.

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Chandra OCR 2 in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

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 Chandra OCR 2

Recommended for the NVIDIA L4: Q6_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q6_K file (opens in a new tab)

huggingface.co/mradermacher/chandra-ocr-2-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/chandra-ocr-2-GGUF:Q6_K

Original weights · Hugging Face

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

huggingface.co/datalab-to/chandra-ocr-2 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Datalab. The weights themselves download from Hugging Face.

github.com/datalab-to/chandra (opens in a new tab)

git clone https://github.com/datalab-to/chandra

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_K, 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 L4: 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.	21.4 / 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.	6.2 / 15
Match score	67.6 / 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 L4

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	4.2 GB	24.0 GB	114 tok/s	Runs great	33Basic quality (D) · 33 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	4.7 GB	24.0 GB	89.8 tok/s	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	5.3 GB	24.0 GB	69.5 tok/s	Runs great	45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	5.8 GB	24.0 GB	57.4 tok/s	Runs great	46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	6.4 GB	24.0 GB	48.2 tok/s	Runs great	47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	7.7 GB	24.0 GB	35.4 tok/s	Runs great	48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	12.7 GB	24.0 GB	16.3 tok/s	Runs well	48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) 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

48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti F16 · 48.7 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 F16 · 52.2 tok/s · Runs great
47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q6_K · 43.7 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q8_0 · 41.1 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q8_0 · 42.4 tok/s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 59.4 tok/s · Runs great

Quick answers

How much memory does Chandra OCR 2 need on the NVIDIA L4 24GB?

At Q6_K it needs about 6.4 GB. The NVIDIA L4 24GB has 24.0 GB usable.

How fast is Chandra OCR 2 on the NVIDIA L4 24GB?

About 48.2 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Chandra OCR 2 should I use on the NVIDIA L4 24GB?

Q6_K. 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.