No — not on this device

Olmo 3.1 32B Instruct at Q4_K_M needs 20.0 GB against 5.4 GB usable, and the shortfall of 14.6 GB is more than 128 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 · 18.1 GB Apache 2.0 Released 10 Dec 2025

The largest fully open model you can audit end to end. Q4 fits 24 GB, tightly.

Hardware requirements What hardware do I need to run Olmo 3.1 32B Instruct? →

At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 32 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 18.1 GB
Weights 18.1 GB KV cache @ 8K 1.25 GB Runtime overhead 0.6 GB Over budget 14.6 GB past 5.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 31.9 GB 33.7 GB — ~1.2 −0.1% ppl 28.3 GB over
Q6_K 24.6 GB 26.4 GB — ~1.5 −0.4% ppl 21.0 GB over
Q5_K_M 21.3 GB 23.1 GB — ~1.8 −0.8% ppl 17.7 GB over
Q4_K_M 18.1 GB 20.0 GB — ~2.1 −1.9% ppl 14.6 GB over
Q3_K_M 14.7 GB 16.5 GB — ~2.6 −5.4% ppl 11.1 GB over
Q2_K 12.6 GB 14.4 GB — ~3.0 −15% ppl 9.0 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, 16 of 64 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-3.1-32B-Instruct-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 18.1 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 M1 · 8 GB

ModelTotalTok/s est.
Olmo 3 7B Instruct
7.3B · same family
Q4_K_M · 7.2 GB — Won't fit
Qwen3 32B
32.8B · similar size
Q4_K_M · 21.0 GB — Won't fit
DeepSeek-R1-Distill-Qwen 32B
32.8B · similar size
Q4_K_M · 21.0 GB — Won't fit
Qwen2.5-Coder 32B
32.8B · similar size
Q4_K_M · 21.0 GB — Won't fit
Nemotron 3.5 Lightning 30B-A3B
31.6B MoE · similar size
Q4_K_M · 18.4 GB — Won't fit
Gemma 4 31B
31.3B · similar size
Q4_K_M · 20.2 GB — Won't fit
LLM-jp 4 33B Thinking
33.2B · similar size
Q4_K_M · 21.3 GB — Won't fit

Every model against the M1 · 8 GB →

Olmo 3.1 32B Instruct on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
20.0 GB ~2.6 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
20.0 GB ~3.4 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
20.0 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
20.0 GB 34 Tight fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
20.0 GB 32 Tight fit
GeForce RTX 5090
30.4 GB usable · 1792 GB/s
20.0 GB 60 Runs great
M4 · 32 GB
24.0 GB usable · 120 GB/s
20.0 GB 3.7 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
20.0 GB 12 Runs great

All 114 devices, by tier →