What can you run with 8GB of RAM?

With 8GB RAM you can run 10 of the 51 open-source models we track — up to about 8.5B parameters at Q4 quantization. The most popular that fits is MiniCPM5-1B, needing 1.3 GB and generating around ~51 tok/s on typical hardware of this size.

Typical machines: Base MacBook Air (M1/M2) · Budget Windows laptops · Entry-level desktops. After the operating system takes its share, about 6.4 GB is free for a model.

Having the memory is not the same as having the speed

8GB RAM decides whether a model loads. How fast it answers is decided by memory bandwidth — how quickly your machine can read the model, which it must do once for every word it writes. Machines with 8GB RAM span 51–102 GB/s, so the fastest is about 2.0× quicker than the slowest with identical capacity. The table quotes a DDR4-3200; pick yours below to see the difference. Why bandwidth and not the processor →

51 GB/sDesktop or older laptop — DDR4-3200· 3,200 MT/s × 128-bit dual channel ÷ 8 = 51.2 GB/s
68 GB/sThin laptop — LPDDR4X-4266· 4,266 MT/s × 128-bit ÷ 8 = 68.3 GB/s (soldered, 2 channels)
68 GB/sMac — M1· Apple published specification for the M1: 68.25 GB/s
90 GB/sDesktop or laptop — DDR5-5600· 5,600 MT/s × 128-bit dual channel ÷ 8 = 89.6 GB/s
100 GB/sMac — M2· Apple published specification for the M2: 100 GB/s
102 GB/sModern thin laptop — LPDDR5-6400· 6,400 MT/s × 128-bit ÷ 8 = 102.4 GB/s (soldered, 2 channels)

Models that run on 8GB RAM in 2026

ModelSizeMemoryEst. speedDownloadsFeels like
LFM2.5-230MLiquid Ai230M808 MBRuns well~216 tok/s58,011Fast
MiniCPM5-1BOpenBMB1.1B1.3 GBRuns well~51 tok/s667,154Fast
MiniCPM5-2BOpenBMB2.5B2.3 GBRuns well~21 tok/s206,774Comfortable
LFM2.5-2.6BLiquid Ai2.7B2.5 GBRuns well~20 tok/s98,713Comfortable
LFM2.5-VL-3BLiquid Ai3.1B2.5 GBRuns well~20 tok/s31,296Comfortable
North-Micro-Vision-InstructCohere2.5B2.5 GBRuns well~22 tok/s120,354Comfortable
granite-4.2-3bIbm3.7B3.1 GBRuns well~15 tok/s32,017Comfortable
Mage-VLMicrosoft4.7B3.9 GBRuns well~12 tok/s29,690Comfortable
LFM2.5-8B-A1BLiquid Ai · MoE8.5B5.9 GBTight~54 tok/s1B active80,632Fast
Ling-3.0-tinyInclusionai · MoE7.9B6.2 GBTight~34 tok/s1.6B active25,727Fast

Sorted by memory, smallest first — click any column to change it.

Upgrade

Including gemma-4-12B-it (12B), Ornith-1.5-9B (9.7B) and granite-4.2-8b (8.8B) — around ~8.1 tok/s on a typical machine that size.

See everything 16GB RAM runs →

All figures at Q4_K_M quantization, 4K context. “Memory” includes the model, its context cache and runtime overhead. Speed is calculated, not benchmarked: 51 GB/s × 0.65 ÷ bytes read per token, assuming a DDR4-3200. Scale it by your own machine's bandwidth from the list above. Mixture-of-experts models read only their active parameters per token, which is why some large ones outrun smaller dense models.

What you'd need more memory for

The next models up, and what they ask for.

granite-4.2-8bneeds 6.6 GB
Ornith-1.5-9Bneeds 6.9 GB
gemma-4-12B-itneeds 9.6 GB
Qwen3.8-27Bneeds 19 GB

Other hardware

Verified against HuggingFace on 2026-09-15New to this? Start here →Runs on a laptop and up · last 120 days only