RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

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.

2.5 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest Mac that fits
4Kmax context
MHAattention type

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.

QuantQuality4K ctx
2-bit (Q2_K) •rough1.7 GB
3-bit (Q3_K_M) •usable1.8 GB
4-bit (Q4_K_M) •good, most popular2.0 GB
5-bit (Q5_K_M) •very good2.1 GB
6-bit (Q6_K) •near lossless2.2 GB
8-bit (Q8_0) •effectively lossless2.6 GB
16-bit (F16/BF16) •original weights3.9 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).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)
RTX 3060 12GB12 GBFitsF164.4 GB121details
RTX 4060 Ti 16GB16 GBFitsF164.4 GB97details
RTX 309024 GBFitsF164.4 GB315details
RTX 409024 GBFitsF164.4 GB339details
RTX 509032 GBFitsF164.4 GB603details
RTX 5070 Ti16 GBFitsF164.4 GB301details
RX 7900 XTX24 GBFitsF164.4 GB323details
Mac M4 Pro 48GB48 GBFitsF164.4 GB92details
Mac M4 Max 128GB128 GBFitsF164.4 GB184details
Mac M3 Ultra 512GB512 GBFitsF164.4 GB275details
DGX Spark128 GBFitsF164.4 GB92details
RTX 407012 GBFitsF164.4 GB169details
RTX 5060 Ti 16GB16 GBFitsF164.4 GB151details
RTX 40608 GBFitsF164.4 GB91details
Arc B58012 GBFitsF164.4 GB153details
RTX 3060 Ti8 GBFitsF164.4 GB151details
RTX 30708 GBFitsF164.4 GB151details
RTX 3080 10GB10 GBFitsF164.4 GB256details
RTX 3080 12GB12 GBFitsF164.4 GB307details
RTX 3090 Ti24 GBFitsF164.4 GB339details
RTX 4060 Ti 8GB8 GBFitsF164.4 GB97details
RTX 4070 Super12 GBFitsF164.4 GB169details
RTX 4070 Ti12 GBFitsF164.4 GB169details
RTX 4070 Ti Super16 GBFitsF164.4 GB226details
RTX 408016 GBFitsF164.4 GB241details
RTX 4080 Super16 GBFitsF164.4 GB248details
RTX 50608 GBFitsF164.4 GB151details
RTX 507012 GBFitsF164.4 GB226details
RTX 508016 GBFitsF164.4 GB323details
2x RTX 30902×24 GBFitsF164.4 GB315details
2x RTX 40902×24 GBFitsF164.4 GB339details
2x RTX 50902×32 GBFitsF164.4 GB603details
RTX A600048 GBFitsF164.4 GB258details
RTX 6000 Ada48 GBFitsF164.4 GB323details
RTX PRO 6000 Blackwell96 GBFitsF164.4 GB603details
L40S48 GBFitsF164.4 GB291details
A100 40GB40 GBFitsF164.4 GB523details
A100 80GB80 GBFitsF164.4 GB686details
H100 PCIe80 GBFitsF164.4 GB673details
H100 SXM80 GBFitsF164.4 GB1127details
H200141 GBFitsF164.4 GB1614details
RX 76008 GBFitsF164.4 GB97details
RX 7700 XT12 GBFitsF164.4 GB145details
RX 7800 XT16 GBFitsF164.4 GB210details
RX 7900 GRE16 GBFitsF164.4 GB194details
RX 7900 XT20 GBFitsF164.4 GB269details
RX 907016 GBFitsF164.4 GB215details
RX 9070 XT16 GBFitsF164.4 GB215details
Ryzen AI Max+ 395 128GB128 GBFitsF164.4 GB86details
Arc A770 16GB16 GBFitsF164.4 GB188details
Mac M1 16GB16 GBFitsF164.4 GB23details
Mac M2 24GB24 GBFitsF164.4 GB34details
Mac M3 24GB24 GBFitsF164.4 GB34details
Mac M4 16GB16 GBFitsF164.4 GB40details
Mac M4 32GB32 GBFitsF164.4 GB40details
Mac M1 Pro 32GB32 GBFitsF164.4 GB67details
Mac M3 Pro 36GB36 GBFitsF164.4 GB50details
Mac M4 Pro 24GB24 GBFitsF164.4 GB92details
Mac M4 Pro 64GB64 GBFitsF164.4 GB92details
Mac M1 Max 64GB64 GBFitsF164.4 GB135details
Mac M2 Max 96GB96 GBFitsF164.4 GB135details
Mac M3 Max 128GB128 GBFitsF164.4 GB135details
Mac M4 Max 64GB64 GBFitsF164.4 GB184details
Mac M2 Ultra 192GB192 GBFitsF164.4 GB269details
Mac M3 Ultra 256GB256 GBFitsF164.4 GB275details

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-bit

OLMoE 1B 7B 0924

6.9B · 5.4 GB at 4-bit

Olmo 3 7B Instruct

7.3B · 7.3 GB at 4-bit

Qwen2.5 1.5B Instruct

1.5B · 1.9 GB at 4-bit

deepseek coder 1.3b instruct

1.3B · 2.8 GB at 4-bit

granite 4.0 1b

1.6B · 2.2 GB at 4-bit

Model facts

Hugging Face repoallenai/OLMo-2-0425-1B
Parameters1,484,916,736 (1.5B)
Layers / hidden size16 / 2048
AttentionMHA; 16 heads, 16 KV heads, head dim 128
KV cache per token (FP16)128.0 KiB
Max context4,096 tokens
Licenseapache-2.0
Released on HFApr 17, 2025
Downloads (30d) / likes117,158 / 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.