Yes — with 202.8 GB to spare

GLM-5.3-Flash 320B-A18B at Q4_K_M fits your M3 Ultra · 512 GB entirely in unified memory at 8K context, at an estimated 21 tokens per second. There is room for its full 1024K window.

Fully in unified memory 8K context Q4_K_M · 180.5 GB MIT Released 25 Aug 2026 Vision Not in the Ollama library

The first natively multimodal GLM-5 and the first hybrid: 34 linear-attention blocks and 11 sparse-attention blocks with a 512-wide latent cache, so a 1M window stays affordable. Z.ai says it beats GLM-5.2 at 18B active; MIT.

Hardware requirements What hardware do I need to run GLM-5.3-Flash 320B-A18B? →

At Q4_K_M with an 8K context: a 512 GB Mac (M3 Ultra). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 180.5 GB
Weights 180.5 GB KV cache @ 8K 0.09 GB Runtime overhead 0.6 GB Free 202.8 GB of 384.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 317.6 GB 318.3 GB 1024K 12 −0.1% ppl Long context
Q6_K 245.1 GB 245.8 GB 1024K 15 −0.4% ppl Long context
Q5_K_M 211.9 GB 212.6 GB 1024K 18 −0.8% ppl Long context
Q4_K_M 180.5 GB 181.2 GB 1024K 21 −1.9% ppl Recommended
Q3_K_M 146.1 GB 146.8 GB 1024K 25 −5.4% ppl Long context
Q2_K 125.2 GB 125.9 GB 1024K 30 −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. Only 11 of its 45 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/GLM-5.3-Flash-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 180.5 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 384.0 GB of 512 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 1024K context on this card.
See all models for this rig Compare with another model

Related models on an M3 Ultra · 512 GB

ModelTotalTok/s est.
GLM-5.2 744B-A40B
753B MoE · same family
Q4_K_M · 424.7 GB — Won't fit
GLM-5.3 744B-A40B
753B MoE · same family
Q4_K_M · 424.7 GB — Won't fit
GLM-4.7-Flash 30B-A3B
31.2B MoE · same family
Q4_K_M · 18.6 GB 124 Runs great
DeepSeek V4 Flash 284B-A13B
284B MoE · similar size
Q4_K_M · 160.7 GB 29 Runs great
Ornith 1.5 397B-A17B
397B MoE · similar size
Q4_K_M · 224.1 GB 22 Runs great
Qwen3.5 397B-A17B
403B MoE · similar size
Q4_K_M · 227.4 GB 22 Runs great
Qwen3 235B-A22B
235B MoE · similar size
Q4_K_M · 134.2 GB 17 Runs great

Every model against the M3 Ultra · 512 GB →

GLM-5.3-Flash 320B-A18B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
181.2 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
181.2 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
181.2 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
181.2 GB — Won't fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
181.2 GB — Won't fit
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
181.2 GB — Won't fit

All 114 devices, by tier →