Yes, just — 5.2 GB spare

Llama 3.3 70B Instruct at Q4_K_M fits your M4 Max · 64 GB entirely in unified memory at 8K context, at an estimated 7.7 tokens per second. Past 24K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

Fully in unified memory 8K context Q4_K_M · 39.7 GB Llama 3.3 Community Released Dec 2024

Still the creative-writing favourite: consistent voice, takes direction. Needs 48 GB to sit comfortably on GPU at Q4.

Hardware requirements What hardware do I need to run Llama 3.3 70B Instruct? →

At Q4_K_M with an 8K context: a 64 GB GPU (Instinct MI210) or a 96 GB Mac (M2 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 39.7 GB
Weights 39.7 GB KV cache @ 8K 2.50 GB Runtime overhead 0.6 GB Free 5.2 GB of 48.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 69.9 GB 73.0 GB — ~4.4 −0.1% ppl 25.0 GB over
Q6_K 53.9 GB 57.0 GB — ~5.7 −0.4% ppl 9.0 GB over
Q5_K_M 46.6 GB 49.7 GB 2K ~6.5 −0.8% ppl 1.7 GB over
Q4_K_M 39.7 GB 42.8 GB 24K 7.7 −1.9% ppl Recommended
Q3_K_M 32.1 GB 35.2 GB 48K 9.5 −5.4% ppl Long context
Q2_K 27.5 GB 30.6 GB 63K 11 −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-3.3-70B-Instruct-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 39.7 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 48.0 GB of 64 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03Only 5.2 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 24K context.
See all models for this rig Compare with another model

Related models on an M4 Max · 64 GB

ModelTotalTok/s est.
Llama 4 Scout 109B-A17B
109B MoE · same family
Q4_K_M · 63.4 GB — Won't fit
Llama 3.1 8B Instruct
8.03B · same family
Q4_K_M · 6.1 GB 68 Runs great
Llama 3.2 3B Instruct
3.21B · same family
Q4_K_M · 3.3 GB 169 Runs great
Llama 3.2 1B Instruct
1.24B · same family
Q4_K_M · 1.5 GB 438 Runs great
DeepSeek-R1-Distill-Llama 70B
70.6B · similar size
Q4_K_M · 42.8 GB 7.7 Tight fit
gpt-oss 120B
117B MoE · similar size
MXFP4 · 61.4 GB — Won't fit
Mistral Small 4 119B-A6B
119B MoE · similar size
Q4_K_M · 67.7 GB — Won't fit

Every model against the M4 Max · 64 GB →

Llama 3.3 70B Instruct on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
42.8 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
42.8 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
42.8 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
42.8 GB ~1.7 CPU offload
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
42.8 GB ~1.7 CPU offload
Instinct MI210
62.4 GB usable · 1638 GB/s
42.8 GB 25 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
42.8 GB 5.6 Tight fit
M2 Max · 96 GB
72.0 GB usable · 400 GB/s
42.8 GB 5.6 Runs great

All 114 devices, by tier →