No — not on this device

Olmo 3 7B Instruct at Q4_K_M needs 7.2 GB against 5.4 GB usable, and the shortfall of 1.8 GB is more than 32 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 4.1 GB Apache 2.0 Released 20 Nov 2025

Fully open — training data and code included. Full multi-head attention, so its cache is 4× a GQA 7B at the same context.

Hardware requirements What hardware do I need to run Olmo 3 7B Instruct? →

At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 4.1 GB
Weights 4.1 GB KV cache @ 8K 2.50 GB Runtime overhead 0.6 GB Over budget 1.8 GB past 5.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 13.6 GB 16.7 GB — ~4.1 Reference 11.3 GB over
Q8_0 7.2 GB 10.3 GB — ~7.7 −0.1% ppl 4.9 GB over
Q6_K 5.6 GB 8.7 GB — ~10 −0.4% ppl 3.3 GB over
Q5_K_M 4.8 GB 7.9 GB — ~12 −0.8% ppl 2.5 GB over
Q4_K_M 4.1 GB 7.2 GB 1K ~14 −1.9% ppl 1.8 GB over
Q3_K_M 3.3 GB 6.4 GB 2K ~17 −5.4% ppl 1.0 GB over
Q2_K 2.8 GB 5.9 GB 3K ~20 −15% ppl 0.5 GB over

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (4096 tokens, 8 of 32 layers global), which is why its cache barely grows with context.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Olmo-3-7B-Instruct-4bit \
    --max-tokens 512 --prompt "Hello"

Apple's own array framework. The fastest path on Apple Silicon. More on MLX.

01Download is 4.1 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 5.4 GB of 8 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on an M2 · 8 GB

ModelTotalTok/s est.
Olmo 3.1 32B Instruct
32.2B · same family
Q4_K_M · 20.0 GB — Won't fit
Mistral 7B Instruct v0.3
7.25B · similar size
Q4_K_M · 5.7 GB — Won't fit
DeepSeek-R1-Distill-Qwen 7B
7.62B · similar size
Q4_K_M · 5.3 GB 13 Tight fit
Qwen2.5-Coder 7B
7.62B · similar size
Q4_K_M · 5.3 GB 13 Tight fit
Ling 3.0 Tiny 7.9B-A1.3B
7.9B MoE · similar size
Q4_K_M · 5.1 GB 36 Tight fit
Gemma 4 E4B
8.0B · similar size
Q4_K_M · 5.2 GB 12 Tight fit
Llama 3.1 8B Instruct
8.03B · similar size
Q4_K_M · 6.1 GB — Won't fit

Every model against the M2 · 8 GB →

Olmo 3 7B Instruct on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
7.2 GB ~32 CPU offload
Arc B570
8.8 GB usable · 380 GB/s
7.2 GB 56 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
7.2 GB 53 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
7.2 GB 16 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
7.2 GB 149 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
7.2 GB 142 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
7.2 GB 54 Runs great

All 114 devices, by tier →