Skip to content

Olmo 3 1025 7B on RTX 5090: VRAM, speed and fit

Olmo 3 1025 7B at 8-bit runs on the RTX 5090 with 64K of context at about 147 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 5090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
17.5 GB
of 32.0 GB
Context
64K
auto
Speed
147 tok/s
67 when full
First reply
0.1 s
2K prompt

Where the memory goes

Model
7.2 GB
Context
9.5 GB
Overhead
785 MB
OS
0.0 GB
Free
14.5 GB
Memory
17.5 GB of 32.0 GB
Context
64K tokens · auto
Speed
147 tok/s · 67 when full
First reply
0.1 s for a 2K prompt
Running cost
$9.30/mo at home · $30/mo on a cloud RTX A4500

Validation: Validated

What Olmo 3 1025 7B on RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory32.0 GB usable17.5 GB neededPass
Headroom5% free14.5 GB free (45%)Pass
Context for chat16K or more64KPass
Writing speed15 tok/s or more147 tok/sPass
First replyunder 3 s, 2K prompt0.1 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
Olmo 3 1025 7B
Parameters
7.3B
Precision
8-bit (Q8_0)
Context
64K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 5090
GPU can use
32.0 GB of 32.0 GB

Running cost

At home
$9.30/mo
425 W at the wall
Renting instead
$30/mo
RTX A4500 at $0.25/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf mradermacher/Olmo-3-1025-7B-i1-GGUF
vLLM
vllm serve allenai/Olmo-3-1025-7B
MLX (Mac)
mlx_lm.chat --model mlx-community/Olmo-3-1025-7B-4bit

Olmo 3 1025 7B on similar machines

All machines: Olmo 3 1025 7B VRAM requirements. Everything that runs here: what can the RTX 5090 run?

Other models that run on RTX 5090

Questions

Can Olmo 3 1025 7B run on RTX 5090?

Olmo 3 1025 7B at 8-bit runs on the RTX 5090 with 64K of context at about 147 tokens a second.

Report VR-0DJCV7I, calculated Nov 22, 2026 from published specs, not benchmarked.