Skip to content

Olmo 3.1 32B on RTX 5090: VRAM, speed and fit

Olmo 3.1 32B at 6-bit runs on the RTX 5090 with 64K of context at about 44 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 5090 · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
30.2 GB
of 32.0 GB
Context
64K
auto
Speed
44 tok/s
37 when full
First reply
0.7 s
2K prompt

Where the memory goes

Model
24.6 GB
Context
4.8 GB
Overhead
817 MB
OS
0.0 GB
Free
1.8 GB
Memory
30.2 GB of 32.0 GB
Context
64K tokens · auto
Speed
44 tok/s · 37 when full
First reply
0.7 s for a 2K prompt
Running cost
$9.30/mo at home · $58/mo on a cloud 2× RTX 2000 Ada

Validation: Validated

What Olmo 3.1 32B on RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory32.0 GB usable30.2 GB neededPass
Headroom5% free1.8 GB free (6%)Pass
Context for chat16K or more64KPass
Writing speed15 tok/s or more44 tok/sPass
First replyunder 3 s, 2K prompt0.7 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 3.1 32B
Parameters
32.2B
Precision
6-bit (Q6_K)
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
$58/mo
2× RTX 2000 Ada at $0.48/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

Ollama
ollama run olmo-3.1:32b-instruct
llama.cpp
llama-server -hf unsloth/Olmo-3.1-32B-Instruct-GGUF
vLLM
vllm serve allenai/Olmo-3.1-32B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Olmo-3.1-32B-Instruct-4bit

Olmo 3.1 32B on similar machines

All machines: Olmo 3.1 32B VRAM requirements. Everything that runs here: what can the RTX 5090 run?

Other models that run on RTX 5090

Questions

Can Olmo 3.1 32B run on RTX 5090?

Olmo 3.1 32B at 6-bit runs on the RTX 5090 with 64K of context at about 44 tokens a second.

Report VR-1EFJKY2, calculated Nov 22, 2026 from published specs, not benchmarked.