OLMo 2 0425 1B — Hardware Requirements & GPU Compatibility
Chat
OLMo 2 1B is Allen AI's smallest base language model in the OLMo 2 family, a 1.48-billion-parameter dense transformer trained on 4 trillion tokens. This is the raw pretrained checkpoint, not an instruction-tuned assistant — Allen AI releases separate SFT, DPO, and RLVR1 versions for chat use. Unusually for an open-weight release, Allen AI also publishes the training data, code, and intermediate checkpoints, making it a reference point for reproducible LLM research. At 1.48B parameters it runs comfortably on modest hardware, even unquantized. It supports a 4,096 token context window, short by current standards. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in April 2025, it is the smallest of four OLMo 2 sizes (1B, 7B, 13B, 32B) sharing the same training recipe and fully open data pipeline.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 4K)Best on 24 GB (Q4_K_M · ~449 tok/s · 4K)Macs from 8 GB (Q4_K_M · ~49 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run OLMo 2 0425 1B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/allenai/OLMo-2-0425-1B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 22.3 GB free · 4K context
Download: OLMo-2-0425-1B-Q4_K_M.gguf0.94 GBallenai
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (10 GB headroom) · Q4_K_M
- Generation speed
- ~160 tok/s
- generation speed
- Cost per 1M output tokens
- $0.14
- per 1M output tokens
How Much VRAM Does OLMo 2 0425 1B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.2 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 4K context · ~546 tok/s | |
| 1.2 GB | — | 3-bit small — 3-bit small quantization | Fits: 4K context · ~537 tok/s | |
| 1.3 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 4K context · ~508 tok/s | |
| 1.3 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 4K context · ~500 tok/s | |
| 1.5 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 4K context · ~449 tok/s | |
| 1.6 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 4K context · ~402 tok/s | |
| 1.8 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 4K context · ~366 tok/s | |
| 2.0 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 4K context · ~320 tok/s |
Selected Q4_K_M
4-bit medium quantization1.7GBat 4K context
- Weights
- 0.9 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.3 GB free · ~449 tok/s
≥50 tok/s needs ≥112 GB/s · RTX 5090 ~798, RTX 3090 Ti ~449
Which Hardware Can Run OLMo 2 0425 1B?
Q4_K_M · 1.5 GBOLMo 2 0425 1B (Q4_K_M) requires 1.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 4K context window can add up to 0.3 GB, bringing total usage to 1.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run OLMo 2 0425 1B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.3 GB free · up to 4K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~339Simulate output on RTX 3080RTX 2080 Ti~274Simulate output on RTX 2080 TiRTX 3070 Ti~271Simulate output on RTX 3070 TiM3*8 GB~49Simulate output on iMac 24" M3 (8 GB)Orin Nano~45Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~33Simulate output on iPhone 1720 GB
fits · 18.3 GB free · up to 4K ctx
1 GPU
RX 7900 XT~329Simulate output on RX 7900 XT32–40 GB
fits · 30.3 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~798Simulate output on RTX 5090M5 Max36 GB~221Simulate output on Mac Studio M5 Max (36 GB)M532 GB~74Simulate output on MacBook Air 13" M5 (32 GB)Orin~91Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~60Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to OLMo 2 0425 1B
OLMo family · 20 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 1BOpenBMB | — | 1.6 GB | ~512 | same size |
| LFM2 VL 1.6BLiquid AI | — | 1.5 GB | ~496 | same size |
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | same size |
| Sweep Next Edit 1.5BXenova | — | 1.6 GB | ~551 | same size |
| Ouro 1.4BByteDance | — | 6.4 GB | ~184 | same size |
| Qwen Base Invoicev1.01 1.5BLaaP-ai | — | 1.7 GB | ~512 | same size |
Specifications
- Publisher
- Allen AI
- Family
- OLMo
- Parameters
- 1.5B
- Architecture
- Olmo2ForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 100,352
- Release Date
- 2025-04-17
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does OLMo 2 0425 1B need?
OLMo 2 0425 1B requires 1.5 GB of VRAM at Q4_K_M, or 3.5 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.5B × 4.8 bits ÷ 8 = 0.9 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 0.8 GB (at full 4K context)
VRAM usage by quantization
What's the best quantization for OLMo 2 0425 1B?
For OLMo 2 0425 1B, Q4_K_M (1.5 GB) offers the best balance of quality and VRAM usage. Q5_0 (1.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run OLMo 2 0425 1B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run OLMo 2 0425 1B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run OLMo 2 0425 1B locally?
Yes — OLMo 2 0425 1B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is OLMo 2 0425 1B?
At Q4_K_M, OLMo 2 0425 1B can reach ~3288 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~449 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 1.46 × 0.65 = ~3562 tok/s
Estimated speed at Q4_K_M (1.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of OLMo 2 0425 1B?
At Q4_K_M, the download is about 0.89 GB. The full-precision BF16 version is 2.97 GB. The smallest option (IQ2_XXS) is 0.41 GB.
Which GPUs can run OLMo 2 0425 1B?
52 consumer GPUs can run OLMo 2 0425 1B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run OLMo 2 0425 1B?
163 devices with unified memory can run OLMo 2 0425 1B at Q4_K_M (1.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.