Skip to content

Muse Spark Open 816B A42B on M3 Ultra 256 GB: VRAM, speed and fit

Muse Spark Open 816B A42B at 1.6-bit runs on the M3 Ultra 256 GB with 352K of context at about 40 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M3 Ultra 256 GB · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat

GPU memory
245 GB
of 256 GB
Context
352K
auto
Speed
40 tok/s
14 when full
First reply
26 s
2K prompt

Where the memory goes

Model
158 GB
Context
22.4 GB
Overhead
907 MB
OS
64.0 GB
Free
10.9 GB
Memory
245 GB of 256 GB
Context
352K tokens · auto
Speed
40 tok/s · 14 when full
First reply
26 s for a 2K prompt
Running cost
$3.55/mo at home · $287/mo on a cloud 4× A40

Validation: Not validated

What Muse Spark Open 816B A42B on M3 Ultra 256 GB was checked against
CheckTargetResultStatus
Fits in GPU memory192 GB usable181 GB neededPass
Headroom5% free10.9 GB free (6%)Pass
Context for chat16K or more352KPass
Writing speed15 tok/s or more40 tok/sPass
First replyunder 3 s, 2K prompt26 sFails

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Muse Spark Open 816B A42B
Parameters
822B, 42B active
Precision
1.6-bit (IQ1_S)
Context
352K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M3 Ultra 256 GB
GPU can use
192 GB of 256 GB

Running cost

At home
$3.55/mo
162 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/Muse-Spark-Open-816B-A42B-GGUF
vLLM
vllm serve meta-models/Muse-Spark-Open-816B-A42B
MLX (Mac)
mlx_lm.chat --model mlx-community/Muse-Spark-Open-816B-A42B-4bit

Muse Spark Open 816B A42B on similar machines

  • Mac mini M4 Pro 64 GBToo big
  • M4 Max 128 GBToo big
  • M5 Max 128 GBToo big
  • M3 Ultra 96 GBToo big
  • M3 Ultra 512 GBRuns
  • M5 Ultra 512 GBRuns
  • Ryzen AI Max+ 395 64 GBToo big
  • Ryzen AI Max+ 395 128 GBToo big

All machines: Muse Spark Open 816B A42B VRAM requirements. Everything that runs here: what can the M3 Ultra 256 GB run?

Other models that run on M3 Ultra 256 GB

Questions

Can Muse Spark Open 816B A42B run on M3 Ultra 256 GB?

Muse Spark Open 816B A42B at 1.6-bit runs on the M3 Ultra 256 GB with 352K of context at about 40 tokens a second.

Report VR-0NKS34H, calculated Nov 22, 2026 from published specs, not benchmarked.