Skip to content

Granite 3.1 3B A800m Instruct on RTX 3080 10 GB: VRAM, speed and fit

Granite 3.1 3B A800m Instruct at 8-bit runs on the RTX 3080 10 GB with 88K of context at about 271 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
9.4 GB
of 10.0 GB
Context
88K
auto
Speed
271 tok/s
68 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
3.3 GB
Context
5.5 GB
Overhead
605 MB
OS
0.0 GB
Free
661 MB
Memory
9.4 GB of 10.0 GB
Context
88K tokens · auto
Speed
271 tok/s · 68 when full
First reply
0.2 s for a 2K prompt
Running cost
$5.95/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What Granite 3.1 3B A800m Instruct on RTX 3080 10 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.0 GB usable9.4 GB neededPass
Headroom5% free661 MB free (6%)Pass
Context for chat16K or more88KPass
Writing speed15 tok/s or more271 tok/sPass
First replyunder 3 s, 2K prompt0.2 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
Granite 3.1 3B A800m Instruct
Parameters
3.3B, 883M active
Precision
8-bit (Q8_0)
Context
88K, 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 bartowski/granite-3.1-3b-a800m-instruct-GGUF
vLLM
vllm serve ibm-granite/granite-3.1-3b-a800m-instruct

Granite 3.1 3B A800m Instruct on similar machines

All machines: Granite 3.1 3B A800m Instruct 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 Granite 3.1 3B A800m Instruct run on RTX 3080 10 GB?

Granite 3.1 3B A800m Instruct at 8-bit runs on the RTX 3080 10 GB with 88K of context at about 271 tokens a second.

Report VR-1319NG9, calculated Nov 22, 2026 from published specs, not benchmarked.