Inkling Small on RTX PRO 6000 Blackwell: VRAM, speed and fit
Inkling Small at 2-bit runs on the RTX PRO 6000 Blackwell with 4K of context at about 168 tokens a second.
Text generation · Chat · Ollama / LM Studio
Tight fit · on RTX PRO 6000 Blackwell · 2-bit (Q2_K) · Ollama / LM Studio · Chat
98% used
- GPU memory
- 94.5 GB
- of 96.0 GB
- Context
- 4K
- auto
- Speed
- 168 tok/s
- Very fast
- First reply
- 0.6 s
- 2K prompt
Where the memory goes
- Model
- 92.9 GB
- Context
- 672 MB
- Overhead
- 1.0 GB
- OS
- 0.0 GB
- Free
- 1.5 GB
- Memory
- 94.5 GB of 96.0 GB
- Context
- 4K tokens · auto
- Speed
- 168 tok/s · very fast
- First reply
- 0.6 s for a 2K prompt
- Running cost
- $9.63/mo at home · $143/mo on a cloud 2× A40
Validation: Validated with conditions
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 96.0 GB usable | 94.5 GB needed | Pass |
| Headroom | 5% free | 1.5 GB free (2%) | Check |
| Context for chat | 4K or more | 4K | Pass |
| Writing speed | 15 tok/s or more | 168 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.6 s | Pass |
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 Small
- Parameters
- 266B, 11.4B active
- Precision
- 2-bit (Q2_K)
- Context
- 4K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- RTX PRO 6000 Blackwell
- GPU can use
- 96.0 GB of 96.0 GB
Worth trying
- DGX Spark · 128 GB: Runs it with 4K context
- H200 NVL: Runs it with 4K context
- M5 Ultra · 256 GB: Runs it with 4K context
Running cost
- At home
- $9.63/mo
- 440 W at the wall
- Renting instead
- $143/mo
- 2× A40 at $1.18/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-Small-GGUF- vLLM
vllm serve thinkingmachines/Inkling-Small- MLX (Mac)
mlx_lm.chat --model mlx-community/Inkling-Small-mxfp4
Inkling Small on similar machines
- RTX 6000 AdaToo big
- L40SToo big
- 2× RTX 5090Too big
- 4× RTX 3090Just misses
- Mac mini M4 16 GBToo big
- Mac mini M4 24 GBToo big
- Mac mini M4 32 GBToo big
- Mac mini M4 Pro 24 GBToo big
All machines: Inkling Small VRAM requirements. Everything that runs here: what can the RTX PRO 6000 Blackwell run?
Other models that run on RTX PRO 6000 Blackwell
Questions
Can Inkling Small run on RTX PRO 6000 Blackwell?
Inkling Small at 2-bit runs on the RTX PRO 6000 Blackwell with 4K of context at about 168 tokens a second.
Report VR-07XDU6B, calculated Nov 22, 2026 from published specs, not benchmarked.