allenai / olmo2

OLMo-2-0425-1B

Name: OLMo-2-0425-1B architecture and memory requirements
Creator: LLM Bottleneck
License: https://creativecommons.org/licenses/by/4.0/

1.48 billion parameters.

Open in the calculator →

Architecturepublished data

Quick answer

OLMo-2-0425-1B needs about 2.27 GB at Q4_K_M — the format most people download — with 4,096 tokens of context. It fits entirely on 18 of 18 common devices, starting with the NVIDIA GeForce RTX 5070 (12 GB). What else fits in 12 GB. No hardware for it? Rent a GPU that runs it, priced live.

Smallest device that fitsNVIDIA GeForce RTX 507012 GB · 672 GB/s~337 tok/s Faster than you readOpen in the calculator →
Fastest in this listNVIDIA GeForce RTX 509032 GB · 1792 GB/s~900 tok/s Faster than you readOpen in the calculator →

Sized at 4,096 tokens of context with the whole model in device memory, across 18 common devices. Speeds are estimates, not benchmarks.

Find the NVIDIA GeForce RTX 5070, the smallest card listed here that holds it: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.

Weight-file size by format

every format, with its evidence

Format	Size	Range	Basis
FP16	2.97 GB	exact	published data
Q8_0	1.58 GB	exact	published data
Q6_K	1.22 GB	exact	published data
Q5_K_M	1.07 GB	exact	published data
Q5_0	1.05 GB	exact	published data
Q4_K_M	0.94 GB	exact	published data
Q4_0	0.89 GB	exact	published data
Q3_K_M	0.78 GB	exact	published data
Q2_K	0.63 GB	exact	published data

9 of these are published files. Open the pinned GGUF repository ↗

A file size is not the memory a run needs: the KV cache and the runtime reserve come on top, and the calculator adds both.

What the labels mean

published data: Read from a published source — a file's byte count, a model's configuration or a manufacturer's specification — or exact arithmetic on such values. Not a measurement on a machine.
reconstructed size: Weight size reconstructed from the pinned architecture, because no published file exists.
size range: Only a lower and an upper bound are claimed for this weight size.

Hardware ladder

Q4_K_M at 4,096 tokens · 18 of 18 devices hold it entirely

Device	Memory	Verdict	Decode	Calculator
NVIDIA GeForce RTX 5070	2.27 GB of 12 GB	fits	~337 tok/s	Open →
AMD Radeon™ RX 9070 XT	2.27 GB of 16 GB	fits	~368 tok/s	Open →
NVIDIA GeForce RTX 4080	2.27 GB of 16 GB	fits	~360 tok/s	Open →
NVIDIA GeForce RTX 5080	2.27 GB of 16 GB	fits	~482 tok/s	Open →
NVIDIA GeForce RTX 5070 Ti	2.27 GB of 16 GB	fits	~450 tok/s	Open →
NVIDIA GeForce RTX 5060 Ti 16GB	2.27 GB of 16 GB	fits	~225 tok/s	Open →
NVIDIA GeForce RTX 4090	2.27 GB of 24 GB	fits	~506 tok/s	Open →
AMD Radeon™ RX 7900 XTX	2.27 GB of 24 GB	fits	~552 tok/s	Open →
NVIDIA GeForce RTX 3090	2.27 GB of 24 GB	fits	~470 tok/s	Open →
NVIDIA GeForce RTX 5090	2.27 GB of 32 GB	fits	~900 tok/s	Open →
NVIDIA RTX 6000 Ada Generation	2.27 GB of 48 GB	fits	~482 tok/s	Open →
Apple M4 Pro	2.27 GB of 64 GB	fits	~91 tok/s	Open →
Apple M5 Pro	2.27 GB of 64 GB	fits	~96 tok/s	Open →
AMD Ryzen AI Max+ 395 with Radeon 8060S	2.27 GB of 128 GB	fits	~147 tok/s	Open →
Apple M3 Max	2.27 GB of 128 GB	fits	~108 tok/s	Open →
Apple M4 Max	2.27 GB of 128 GB	fits	~120 tok/s	Open →
NVIDIA DGX Spark	2.27 GB of 128 GB	fits	~137 tok/s	Open →
Apple M2 Ultra	2.27 GB of 192 GB	fits	~133 tok/s	Open →

Decode is a calibrated estimate from the published calibration; capacity is the manufacturer's published ceiling, not guaranteed free memory. Fitting in memory is not the same as loading: whether the runtime and version you have supports this architecture and format on that machine has not been tested here. Offloaded rows assume there is enough system RAM for the overflow — the calculator checks that against the RAM you declare. Each “Open” link keeps this model, format and context.

Run it in the cloud

Rent a GPU that runs OLMo-2-0425-1B

Every rentable machine that holds the whole model, from Vast.ai and RunPod, with this site's speed estimate for each and the provider's own price, read live. Cheapest first; sort by cost per token or speed instead, or switch the format.

Prices · 18:30 UTC, 22 Sept

Machine	Speed	Per hour	Per M tokens	Where	Rent
1× RTX 306012 GBrecommendedcheapestbest value	~180 tok/sFaster than you read	$0.036	$0.055	Vast.aiMarketplace · 99.8% reliable	Rent on Vast.ai
1× RTX 308010 GB	~381 tok/sFaster than you read	$0.082	$0.060	Vast.aiMarketplace · 98.3% reliable	Rent on Vast.ai
1× RTX 30708 GB	~224 tok/sFaster than you read	$0.082	$0.10	Vast.aiMarketplace · 99.1% reliableRunPod $0.13/h	Rent on Vast.ai
1× RTX 4060 Ti 16GB16 GB	~144 tok/sFaster than you read	$0.090	$0.17	Vast.aiMarketplace · 99.4% reliable	Rent on Vast.ai
1× RTX 407012 GB	~253 tok/sFaster than you read	$0.096	$0.10	Vast.aiMarketplace · 99.8% reliable	Rent on Vast.ai
1× RTX 309024 GB	~469 tok/sFaster than you read	$0.12	$0.072	Vast.aiMarketplace · 99.5% reliableRunPod $0.50/h	Rent on Vast.ai
1× RTX 5060 Ti 16GB16 GB	~224 tok/sFaster than you read	$0.12	$0.15	Vast.aiMarketplace · 99.1% reliable	Rent on Vast.ai
1× RTX 3080 Ti12 GB	~457 tok/sFaster than you read	$0.14	$0.082	Vast.aiMarketplace · 99.9% reliable	Rent on Vast.ai

First time renting a GPU? How it works, in four steps

Create an account and add credit. Both providers are prepaid: $10 is enough to try any card on this page for hours. A new RunPod account that arrives through a referral link gets a one-time $5 credit when it first adds $10.
Pick the card and the count shown here, and a template: llama.cpp or vLLM for an OpenAI-compatible API, or one with a web chat if you only want to talk to the model. “How to launch it” below gives the exact image and command.
Wait for the download. The weights are fetched on the machine; tens of gigabytes take a few minutes on a data-centre connection. You pay by the second from the moment it starts.
Stop it when you are done. A running machine bills even when idle. A stopped one costs nothing per hour, though its disk is usually still billed until you delete it.

How to launch Q4_K_M on it (llama.cpp)

Container image: ghcr.io/ggml-org/llama.cpp:server-cuda
Start command / arguments: -hf allenai/OLMo-2-0425-1B-GGUF:Q4_K_M -c 4096 -ngl 999 --host 0.0.0.0 --port 8080
Expose port: 8080 — an OpenAI-compatible API at /v1

Starting from a saved llama.cpp template instead? Leave the arguments empty and set these variables — only the first two change between models:

LLAMA_ARG_HF_REPO=allenai/OLMo-2-0425-1B-GGUF:Q4_K_M
LLAMA_ARG_CTX_SIZE=4096
LLAMA_ARG_N_GPU_LAYERS=999
LLAMA_ARG_HOST=0.0.0.0
LLAMA_ARG_PORT=8080

Already have the runtime? llama-server -hf allenai/OLMo-2-0425-1B-GGUF:Q4_K_M -c 4096 -ngl 999 --host 0.0.0.0 --port 8080. Weights: allenai/OLMo-2-0425-1B-GGUF. The CUDA image is for NVIDIA cards; an AMD machine needs llama.cpp's ROCm build.

Every machine holds the whole model at Q4_K_M and 4,096 tokens of context, no offload. Speeds are this site’s single-stream decode estimates; prices are what each provider’s own API quoted, on-demand, for the whole machine. Vast hosts below 98% measured reliability are left out.

Referral links Vast.ai, RunPod and Novita pay us a share of what you spend if you sign up through these buttons. It costs you nothing, and it never decides an order or a recommendation: both are computed from the live price and the speed, and options that pay us nothing are listed and recommended on the same terms. How we rank

Buying a card instead, or paying by the token? Compare a year of OLMo-2-0425-1B three ways →

Under the hood

Architecture, read from the publisher’s file

The numbers every figure above is computed from, with the file they came from.

Architecture

architecture.json · pinned a1847dff3500

✓ Architecture read from the published config.json

Retrieved 2026-09-01 at pinned commit a1847dff3500; parameter count from the safetensors index at the same revision.

Architecture: olmo2
Layers: 16
Hidden size: 2,048
Attention heads: 16
KV heads: 16
Feed-forward width: 8,192
Vocabulary: 100,352
Context ceiling: 4,096
RoPE theta: 500,000

Where the memory goes

Every attention head caches its own keys and values, so the KV cache grows at the full multi-head rate with context.

Open the exact official config.json ↗

More from allenai

OLMo-2-0325-32B-Instruct Olmo-3-7B-Instruct OLMoE-1B-7B-0125-Instruct

Use this answer in your own product

As JSON, from the API

curl -s https://llmbottleneck.com/v1/analyze \
  -H "Authorization: Bearer $LLMB_KEY" -H "content-type: application/json" \
  -d '{"model":"allenai-olmo-2-0425-1b","quantization":"Q4_K_M","context":4096,"hardware":"nvidia-geforce-rtx-4090"}'

Same engine, same evidence, every field sourced. Free key in one step →

On your page, as a widget

<script src="https://llmbottleneck.com/widget.js"
  data-model="allenai-olmo-2-0425-1b" data-quantization="Q4_K_M"
  data-hardware="nvidia-geforce-rtx-4090" data-context="4096"></script>

No key needed. Unbranded, with your own buy button, on Pro and Business →

Citing this page

LLM Bottleneck. “OLMo-2-0425-1B VRAM and hardware requirements.” Architecture from allenai/OLMo-2-0425-1B at revision a1847dff3500, retrieved 2026-09-01. https://llmbottleneck.com/models/allenai-olmo-2-0425-1b

Every figure above is either the published value or a reconstruction whose measured error is on the accuracy page.