Skip to content

Chandra OCR 2 on RTX 3080 10 GB: VRAM, speed and fit

Chandra OCR 2 at 8-bit runs on the RTX 3080 10 GB with 96K of context at about 86 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 3080 10 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
9.3 GB
of 10.0 GB
Context
96K
auto
Speed
86 tok/s
57 when full
First reply
0.3 s
2K prompt

Where the memory goes

Model
5.2 GB
Context
3.0 GB
Overhead
1.0 GB
OS
0.0 GB
Free
727 MB
Memory
9.3 GB of 10.0 GB
Context
96K tokens · auto
Speed
86 tok/s · 57 when full
First reply
0.3 s for a 2K prompt
Running cost
$5.95/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What Chandra OCR 2 on RTX 3080 10 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.0 GB usable9.3 GB neededPass
Headroom5% free727 MB free (7%)Pass
Context for chat16K or more96KPass
Writing speed15 tok/s or more86 tok/sPass
First replyunder 3 s, 2K prompt0.3 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Chandra OCR 2
Parameters
5.3B
Precision
8-bit (Q8_0)
Context
96K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 3080 10 GB
GPU can use
10.0 GB of 10.0 GB

Running cost

At home
$5.95/mo
272 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf prithivMLmods/chandra-ocr-2-GGUF
vLLM
vllm serve datalab-to/chandra-ocr-2

Chandra OCR 2 on similar machines

All machines: Chandra OCR 2 VRAM requirements. Everything that runs here: what can the RTX 3080 10 GB run?

Other models that run on RTX 3080 10 GB

Questions

Can Chandra OCR 2 run on RTX 3080 10 GB?

Chandra OCR 2 at 8-bit runs on the RTX 3080 10 GB with 96K of context at about 86 tokens a second.

Report VR-0VAWVIT, calculated Nov 22, 2026 from published specs, not benchmarked.