No — not on this device

Ornith 1.5 35B-A3B at Q4_K_M needs 20.9 GB against 10.7 GB usable, and the shortfall of 10.2 GB is more than 32 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 · 20.2 GB MIT Released 19 Aug 2026 New this week

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

What hardware do I need for Ornith 1.5 35B-A3B? →

Fits instead: Ornith 1.5 9B (6.1 GB)

The VRAM budget

weights 20.2 GB
Weights 20.2 GB KV cache @ 8K 0.16 GB Runtime overhead 0.6 GB Over budget 10.2 GB past 10.7 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 35.5 GB 36.3 GB ~5.4 −0.1% ppl 25.6 GB over
Q6_K 27.4 GB 28.2 GB ~7.0 −0.4% ppl 17.5 GB over
Q5_K_M 23.7 GB 24.5 GB ~8.1 −0.8% ppl 13.8 GB over
Q4_K_M 20.2 GB 20.9 GB ~9.6 −1.9% ppl 10.2 GB over
Q3_K_M 16.3 GB 17.1 GB ~12 −5.4% ppl 6.4 GB over
Q2_K 14.0 GB 14.8 GB ~14 −15% ppl 4.1 GB over

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 10.7 GB of 16 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