Yes, just — 3.1 GB spare

Ornith 1.5 35B-A3B at Q4_K_M fits your M4 · 32 GB entirely in unified memory at 8K context, at an estimated 17 tokens per second. Past 164K 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 · 20.2 GB MIT Released 19 Aug 2026

A reasoning-first MIT build on the Qwen3.6 35B-A3B architecture (thinks before every answer). Same VRAM as its base.

Hardware requirements What hardware do I need to run Ornith 1.5 35B-A3B? →

At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 20.2 GB
Weights 20.2 GB KV cache @ 8K 0.16 GB Runtime overhead 0.6 GB Free 3.1 GB of 24.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 35.5 GB 36.3 GB — ~9.6 −0.1% ppl 12.3 GB over
Q6_K 27.4 GB 28.2 GB — ~12 −0.4% ppl 4.2 GB over
Q5_K_M 23.7 GB 24.5 GB — ~14 −0.8% ppl 0.5 GB over
Q4_K_M 20.2 GB 20.9 GB 164K 17 −1.9% ppl Recommended
Q3_K_M 16.3 GB 17.1 GB 256K 21 −5.4% ppl Long context
Q2_K 14.0 GB 14.8 GB 256K 24 −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 10 of its 40 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.

How to run it

terminal
$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Ornith-1.5-35B-A3B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 20.2 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 24.0 GB of 32 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03Only 3.1 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 164K context.
See all models for this rig Compare with another model

Related models on an M4 · 32 GB

ModelTotalTok/s est.
Ornith 1.5 9B
9.41B · same family
Q4_K_M · 6.1 GB 13 Runs great
Ornith 1.5 397B-A17B
397B MoE · same family
Q4_K_M · 224.1 GB — Won't fit
Qwen3.6 35B-A3B
35.9B MoE · similar size
Q4_K_M · 20.9 GB 17 Tight fit
LLM-jp 4 33B Thinking
33.2B · similar size
Q4_K_M · 21.3 GB 3.6 Tight fit
Qwen3 32B
32.8B · similar size
Q4_K_M · 21.0 GB 3.6 Tight fit
DeepSeek-R1-Distill-Qwen 32B
32.8B · similar size
Q4_K_M · 21.0 GB 3.6 Tight fit
Qwen2.5-Coder 32B
32.8B · similar size
Q4_K_M · 21.0 GB 3.6 Tight fit

Every model against the M4 · 32 GB →

Ornith 1.5 35B-A3B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
20.9 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
20.9 GB ~13 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
20.9 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
20.9 GB 126 Tight fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
20.9 GB 120 Tight fit
GeForce RTX 5090
30.4 GB usable · 1792 GB/s
20.9 GB 225 Runs great
M4 Max · 36 GB
27.0 GB usable · 410 GB/s
20.9 GB 58 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
20.9 GB 56 Runs great

All 114 devices, by tier →