Yes — with 137.9 GB to spare

Llama 3.1 8B Instruct at Q4_K_M fits your M2 Ultra · 192 GB entirely in unified memory at 8K context, at an estimated 99 tokens per second. There is room for its full 128K window.

Fully in unified memory 8K context Q4_K_M · 4.5 GB Llama 3.1 Community Released Jul 2024

Still the most widely deployed local model, with the largest fine-tune ecosystem. Not the strongest 8B any more.

Hardware requirements What hardware do I need to run Llama 3.1 8B 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 4.5 GB
Weights 4.5 GB KV cache @ 8K 1.00 GB Runtime overhead 0.6 GB Free 137.9 GB of 144.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 15.0 GB 16.6 GB 128K 30 Reference Long context
Q8_0 7.9 GB 9.5 GB 128K 56 −0.1% ppl Long context
Q6_K 6.1 GB 7.7 GB 128K 73 −0.4% ppl Long context
Q5_K_M 5.3 GB 6.9 GB 128K 84 −0.8% ppl Long context
Q4_K_M 4.5 GB 6.1 GB 128K 99 −1.9% ppl Recommended
Q3_K_M 3.7 GB 5.3 GB 128K 122 −5.4% ppl Long context
Q2_K 3.1 GB 4.7 GB 128K 143 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Llama-3.1-8B-Instruct-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 4.5 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 144.0 GB of 192 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 128K context on this card.
See all models for this rig Compare with another model

Related models on an M2 Ultra · 192 GB

ModelTotalTok/s est.
Llama 3.2 3B Instruct
3.21B · same family
Q4_K_M · 3.3 GB 248 Runs great
Llama 3.2 1B Instruct
1.24B · same family
Q4_K_M · 1.5 GB 641 Runs great
Llama 3.3 70B Instruct
70.6B · same family
Q4_K_M · 42.8 GB 11 Runs great
Llama 4 Scout 109B-A17B
109B MoE · same family
Q4_K_M · 63.4 GB 22 Runs great
Gemma 4 E4B
8.0B · similar size
Q4_K_M · 5.2 GB 99 Runs great
Ling 3.0 Tiny 7.9B-A1.3B
7.9B MoE · similar size
Q4_K_M · 5.1 GB 285 Runs great
Qwen3 8B
8.19B · similar size
Q4_K_M · 6.3 GB 97 Runs great

Every model against the M2 Ultra · 192 GB →

Llama 3.1 8B Instruct on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
6.1 GB 34 Tight fit
Arc B570
8.8 GB usable · 380 GB/s
6.1 GB 51 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
6.1 GB 48 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
6.1 GB 15 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
6.1 GB 135 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
6.1 GB 129 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
6.1 GB 50 Runs great

All 114 devices, by tier →