Can I run OLMo 2 0425 1B locally?
OLMo 2 0425 1B by allenai has 1.5B parameters. At 4-bit with an 8K context it needs about 2.5 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from allenai/OLMo-2-0425-1B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx |
|---|---|---|
| 2-bit (Q2_K) • | rough | 1.7 GB |
| 3-bit (Q3_K_M) • | usable | 1.8 GB |
| 4-bit (Q4_K_M) • | good, most popular | 2.0 GB |
| 5-bit (Q5_K_M) • | very good | 2.1 GB |
| 6-bit (Q6_K) • | near lossless | 2.2 GB |
| 8-bit (Q8_0) • | effectively lossless | 2.6 GB |
| 16-bit (F16/BF16) • | original weights | 3.9 GB |
Which GPUs and Macs run OLMo 2 0425 1B?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
| Hardware | Memory | Fits? | Best quant | Needs | Max tok/s (est.) | |
|---|---|---|---|---|---|---|
| RTX 3060 12GB | 12 GB | Fits | F16 | 4.4 GB | 121 | details |
| RTX 4060 Ti 16GB | 16 GB | Fits | F16 | 4.4 GB | 97 | details |
| RTX 3090 | 24 GB | Fits | F16 | 4.4 GB | 315 | details |
| RTX 4090 | 24 GB | Fits | F16 | 4.4 GB | 339 | details |
| RTX 5090 | 32 GB | Fits | F16 | 4.4 GB | 603 | details |
| RTX 5070 Ti | 16 GB | Fits | F16 | 4.4 GB | 301 | details |
| RX 7900 XTX | 24 GB | Fits | F16 | 4.4 GB | 323 | details |
| Mac M4 Pro 48GB | 48 GB | Fits | F16 | 4.4 GB | 92 | details |
| Mac M4 Max 128GB | 128 GB | Fits | F16 | 4.4 GB | 184 | details |
| Mac M3 Ultra 512GB | 512 GB | Fits | F16 | 4.4 GB | 275 | details |
| DGX Spark | 128 GB | Fits | F16 | 4.4 GB | 92 | details |
| RTX 4070 | 12 GB | Fits | F16 | 4.4 GB | 169 | details |
| RTX 5060 Ti 16GB | 16 GB | Fits | F16 | 4.4 GB | 151 | details |
| RTX 4060 | 8 GB | Fits | F16 | 4.4 GB | 91 | details |
| Arc B580 | 12 GB | Fits | F16 | 4.4 GB | 153 | details |
| RTX 3060 Ti | 8 GB | Fits | F16 | 4.4 GB | 151 | details |
| RTX 3070 | 8 GB | Fits | F16 | 4.4 GB | 151 | details |
| RTX 3080 10GB | 10 GB | Fits | F16 | 4.4 GB | 256 | details |
| RTX 3080 12GB | 12 GB | Fits | F16 | 4.4 GB | 307 | details |
| RTX 3090 Ti | 24 GB | Fits | F16 | 4.4 GB | 339 | details |
| RTX 4060 Ti 8GB | 8 GB | Fits | F16 | 4.4 GB | 97 | details |
| RTX 4070 Super | 12 GB | Fits | F16 | 4.4 GB | 169 | details |
| RTX 4070 Ti | 12 GB | Fits | F16 | 4.4 GB | 169 | details |
| RTX 4070 Ti Super | 16 GB | Fits | F16 | 4.4 GB | 226 | details |
| RTX 4080 | 16 GB | Fits | F16 | 4.4 GB | 241 | details |
| RTX 4080 Super | 16 GB | Fits | F16 | 4.4 GB | 248 | details |
| RTX 5060 | 8 GB | Fits | F16 | 4.4 GB | 151 | details |
| RTX 5070 | 12 GB | Fits | F16 | 4.4 GB | 226 | details |
| RTX 5080 | 16 GB | Fits | F16 | 4.4 GB | 323 | details |
| 2x RTX 3090 | 2×24 GB | Fits | F16 | 4.4 GB | 315 | details |
| 2x RTX 4090 | 2×24 GB | Fits | F16 | 4.4 GB | 339 | details |
| 2x RTX 5090 | 2×32 GB | Fits | F16 | 4.4 GB | 603 | details |
| RTX A6000 | 48 GB | Fits | F16 | 4.4 GB | 258 | details |
| RTX 6000 Ada | 48 GB | Fits | F16 | 4.4 GB | 323 | details |
| RTX PRO 6000 Blackwell | 96 GB | Fits | F16 | 4.4 GB | 603 | details |
| L40S | 48 GB | Fits | F16 | 4.4 GB | 291 | details |
| A100 40GB | 40 GB | Fits | F16 | 4.4 GB | 523 | details |
| A100 80GB | 80 GB | Fits | F16 | 4.4 GB | 686 | details |
| H100 PCIe | 80 GB | Fits | F16 | 4.4 GB | 673 | details |
| H100 SXM | 80 GB | Fits | F16 | 4.4 GB | 1127 | details |
| H200 | 141 GB | Fits | F16 | 4.4 GB | 1614 | details |
| RX 7600 | 8 GB | Fits | F16 | 4.4 GB | 97 | details |
| RX 7700 XT | 12 GB | Fits | F16 | 4.4 GB | 145 | details |
| RX 7800 XT | 16 GB | Fits | F16 | 4.4 GB | 210 | details |
| RX 7900 GRE | 16 GB | Fits | F16 | 4.4 GB | 194 | details |
| RX 7900 XT | 20 GB | Fits | F16 | 4.4 GB | 269 | details |
| RX 9070 | 16 GB | Fits | F16 | 4.4 GB | 215 | details |
| RX 9070 XT | 16 GB | Fits | F16 | 4.4 GB | 215 | details |
| Ryzen AI Max+ 395 128GB | 128 GB | Fits | F16 | 4.4 GB | 86 | details |
| Arc A770 16GB | 16 GB | Fits | F16 | 4.4 GB | 188 | details |
| Mac M1 16GB | 16 GB | Fits | F16 | 4.4 GB | 23 | details |
| Mac M2 24GB | 24 GB | Fits | F16 | 4.4 GB | 34 | details |
| Mac M3 24GB | 24 GB | Fits | F16 | 4.4 GB | 34 | details |
| Mac M4 16GB | 16 GB | Fits | F16 | 4.4 GB | 40 | details |
| Mac M4 32GB | 32 GB | Fits | F16 | 4.4 GB | 40 | details |
| Mac M1 Pro 32GB | 32 GB | Fits | F16 | 4.4 GB | 67 | details |
| Mac M3 Pro 36GB | 36 GB | Fits | F16 | 4.4 GB | 50 | details |
| Mac M4 Pro 24GB | 24 GB | Fits | F16 | 4.4 GB | 92 | details |
| Mac M4 Pro 64GB | 64 GB | Fits | F16 | 4.4 GB | 92 | details |
| Mac M1 Max 64GB | 64 GB | Fits | F16 | 4.4 GB | 135 | details |
| Mac M2 Max 96GB | 96 GB | Fits | F16 | 4.4 GB | 135 | details |
| Mac M3 Max 128GB | 128 GB | Fits | F16 | 4.4 GB | 135 | details |
| Mac M4 Max 64GB | 64 GB | Fits | F16 | 4.4 GB | 184 | details |
| Mac M2 Ultra 192GB | 192 GB | Fits | F16 | 4.4 GB | 269 | details |
| Mac M3 Ultra 256GB | 256 GB | Fits | F16 | 4.4 GB | 275 | details |
Questions
How much VRAM does OLMo 2 0425 1B need?
About 2.5 GB at 4-bit (Q4_K_M) with an 8K context: 0.9 GB of weights (real GGUF file size), 1.0 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 3.1 GB.
What is the smallest GPU that runs OLMo 2 0425 1B?
At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).
Can I run OLMo 2 0425 1B on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Molmo2 4B
4.9B · 4.3 GB at 4-bitOLMoE 1B 7B 0924
6.9B · 5.4 GB at 4-bitOlmo 3 7B Instruct
7.3B · 7.3 GB at 4-bitQwen2.5 1.5B Instruct
1.5B · 1.9 GB at 4-bitdeepseek coder 1.3b instruct
1.3B · 2.8 GB at 4-bitgranite 4.0 1b
1.6B · 2.2 GB at 4-bitModel facts
| Hugging Face repo | allenai/OLMo-2-0425-1B |
| Parameters | 1,484,916,736 (1.5B) |
| Layers / hidden size | 16 / 2048 |
| Attention | MHA; 16 heads, 16 KV heads, head dim 128 |
| KV cache per token (FP16) | 128.0 KiB |
| Max context | 4,096 tokens |
| License | apache-2.0 |
| Released on HF | Apr 17, 2025 |
| Downloads (30d) / likes | 117,158 / 83 |
Sources: Hugging Face model API · config.json (allenai/OLMo-2-0425-1B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.