Skip to content

Qari OCR V0.3 VL 2B Instruct on RTX 4060: VRAM, speed and fit

Qari OCR V0.3 VL 2B Instruct at 8-bit runs on the RTX 4060 with 32K of context at about 76 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 4060 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
3.8 GB
of 8.0 GB
Context
32K
auto
Speed
76 tok/s
55 when full
First reply
0.3 s
2K prompt

Where the memory goes

Model
2.2 GB
Context
896 MB
Overhead
806 MB
OS
0.0 GB
Free
4.2 GB
Memory
3.8 GB of 8.0 GB
Context
32K tokens · auto
Speed
76 tok/s · 55 when full
First reply
0.3 s for a 2K prompt
Running cost
$3.26/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What Qari OCR V0.3 VL 2B Instruct on RTX 4060 was checked against
CheckTargetResultStatus
Fits in GPU memory8.0 GB usable3.8 GB neededPass
Headroom5% free4.2 GB free (52%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more76 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
Qari OCR V0.3 VL 2B Instruct
Parameters
2.2B
Precision
8-bit (Q8_0)
Context
32K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 4060
GPU can use
8.0 GB of 8.0 GB

Running cost

At home
$3.26/mo
149 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 mradermacher/Qari-OCR-0.3-SNAPSHOT-VL-2B-Instruct-merged-GGUF
vLLM
vllm serve NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct

Qari OCR V0.3 VL 2B Instruct on similar machines

All machines: Qari OCR V0.3 VL 2B Instruct VRAM requirements. Everything that runs here: what can the RTX 4060 run?

Other models that run on RTX 4060

Questions

Can Qari OCR V0.3 VL 2B Instruct run on RTX 4060?

Qari OCR V0.3 VL 2B Instruct at 8-bit runs on the RTX 4060 with 32K of context at about 76 tokens a second.

Report VR-029Z8KO, calculated Nov 22, 2026 from published specs, not benchmarked.