No — not on this device

Llama 4 Scout 109B-A17B at Q4_K_M needs 63.4 GB against 48.0 GB usable, and the shortfall of 15.4 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 · 61.3 GB Llama 4 Community Released 5 Apr 2025 Vision

A 10M-token window on paper, chunked attention in practice (8K chunks on 3 of 4 layers). Needs 64 GB+ at Q4.

Hardware requirements What hardware do I need to run Llama 4 Scout 109B-A17B? →

At Q4_K_M with an 8K context: a 80 GB GPU (H100 SXM) or a 128 GB Mac. Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

Fits instead: Llama 3.3 70B Instruct (42.8 GB) · Llama 3.1 8B Instruct (6.1 GB)

The VRAM budget

weights 61.3 GB
Weights 61.3 GB KV cache @ 8K 1.50 GB Runtime overhead 0.6 GB Over budget 15.4 GB past 48.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 107.9 GB 110.0 GB — ~6.2 −0.1% ppl 62.0 GB over
Q6_K 83.2 GB 85.3 GB — ~8.0 −0.4% ppl 37.3 GB over
Q5_K_M 71.9 GB 74.0 GB — ~9.3 −0.8% ppl 26.0 GB over
Q4_K_M 61.3 GB 63.4 GB — ~11 −1.9% ppl 15.4 GB over
Q3_K_M 49.6 GB 51.7 GB — ~13 −5.4% ppl 3.7 GB over
Q2_K 42.5 GB 44.6 GB 80K 16 −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. This model interleaves sliding-window layers (8192 tokens, 12 of 48 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/Llama-4-Scout-17B-16E-Instruct-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 61.3 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.
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 M3 Max · 64 GB

ModelTotalTok/s est.
Llama 3.3 70B Instruct
70.6B · same family
Q4_K_M · 42.8 GB 5.6 Tight fit
Llama 3.1 8B Instruct
8.03B · same family
Q4_K_M · 6.1 GB 50 Runs great
Llama 3.2 3B Instruct
3.21B · same family
Q4_K_M · 3.3 GB 124 Runs great
Llama 3.2 1B Instruct
1.24B · same family
Q4_K_M · 1.5 GB 321 Runs great
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
Nemotron 3 Super 120B-A12B
124B MoE · similar size
Q4_K_M · 70.4 GB — Won't fit

Every model against the M3 Max · 64 GB →

Llama 4 Scout 109B-A17B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
63.4 GB ~1.6 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
63.4 GB ~1.7 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
63.4 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
63.4 GB ~2.1 CPU offload
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
63.4 GB ~2.1 CPU offload
H100 SXM
78.4 GB usable · 3350 GB/s
63.4 GB 82 Runs great
DGX Spark · 128 GB
96.0 GB usable · 273 GB/s
63.4 GB 7.4 Runs great

All 114 devices, by tier →