Inkling on M3 Ultra 256 GB: VRAM, speed and fit
Inkling at 1.6-bit runs on the M3 Ultra 256 GB with 4K of context at about 40 tokens a second.
Text generation · Chat · Ollama / LM Studio
Tight fit · on M3 Ultra 256 GB · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat
96% used
- GPU memory
- 249 GB
- of 256 GB
- Context
- 4K
- auto
- Speed
- 40 tok/s
- Fast
- First reply
- 25 s
- 2K prompt
Where the memory goes
- Model
- 183 GB
- Context
- 1.0 GB
- Overhead
- 841 MB
- OS
- 64.0 GB
- Free
- 7.2 GB
- Memory
- 249 GB of 256 GB
- Context
- 4K tokens · auto
- Speed
- 40 tok/s · fast
- First reply
- 25 s for a 2K prompt
- Running cost
- $3.55/mo at home · $287/mo on a cloud 4× A40
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 192 GB usable | 185 GB needed | Pass |
| Headroom | 5% free | 7.2 GB free (4%) | Check |
| Context for chat | 4K or more | 4K | Pass |
| Writing speed | 15 tok/s or more | 40 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 25 s | Fails |
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
- Inkling
- Parameters
- 952B, 40.9B active
- Precision
- 1.6-bit (IQ1_S)
- Context
- 4K, 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
Worth trying
- DGX Station GB300: Runs it with 4K context
- 2× H200 NVL: Runs it with 4K context
- M5 Ultra · 512 GB: Runs it with 4K context
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/inkling-GGUF- vLLM
vllm serve thinkingmachines/Inkling- Model card
- huggingface.co/thinkingmachines/Inkling
Inkling 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: Inkling 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 Inkling run on M3 Ultra 256 GB?
Inkling at 1.6-bit runs on the M3 Ultra 256 GB with 4K of context at about 40 tokens a second.
Report VR-0PNE4MU, calculated Nov 22, 2026 from published specs, not benchmarked.