EXAONE 3.5 7.8B Instruct on RTX PRO 5000 Blackwell 48 GB: VRAM, speed and fit
EXAONE 3.5 7.8B Instruct at 8-bit runs on the RTX PRO 5000 Blackwell 48 GB with 32K of context at about 107 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on RTX PRO 5000 Blackwell 48 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 12.5 GB
- of 48.0 GB
- Context
- 32K
- auto
- Speed
- 107 tok/s
- 72 when full
- First reply
- 0.2 s
- 2K prompt
Where the memory goes
- Model
- 7.7 GB
- Context
- 4.0 GB
- Overhead
- 789 MB
- OS
- 0.0 GB
- Free
- 35.5 GB
- Memory
- 12.5 GB of 48.0 GB
- Context
- 32K tokens · auto
- Speed
- 107 tok/s · 72 when full
- First reply
- 0.2 s for a 2K prompt
- Running cost
- $5.69/mo at home · $29/mo on a cloud RTX 2000 Ada
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 48.0 GB usable | 12.5 GB needed | Pass |
| Headroom | 5% free | 35.5 GB free (74%) | Pass |
| Context for chat | 16K or more | 32K | Pass |
| Writing speed | 15 tok/s or more | 107 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.2 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
- EXAONE 3.5 7.8B Instruct
- Parameters
- 7.8B
- Precision
- 8-bit (Q8_0)
- Context
- 32K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- RTX PRO 5000 Blackwell 48 GB
- GPU can use
- 48.0 GB of 48.0 GB
Running cost
- At home
- $5.69/mo
- 260 W at the wall
- Renting instead
- $29/mo
- RTX 2000 Ada at $0.24/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 lmstudio-community/EXAONE-3.5-7.8B-Instruct-GGUF- vLLM
vllm serve LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct- MLX (Mac)
mlx_lm.chat --model mlx-community/EXAONE-3.5-7.8B-Instruct-3bit
EXAONE 3.5 7.8B Instruct on similar machines
- Radeon AI PRO R9700Runs
- RTX 5090Runs
- 2× RTX 3090Runs
- 2× RTX 4090Runs
- RTX 6000 AdaRuns
- L40SRuns
- 2× RTX 5090Runs
- 4× RTX 3090Runs
All machines: EXAONE 3.5 7.8B Instruct VRAM requirements. Everything that runs here: what can the RTX PRO 5000 Blackwell 48 GB run?
Other models that run on RTX PRO 5000 Blackwell 48 GB
Questions
Can EXAONE 3.5 7.8B Instruct run on RTX PRO 5000 Blackwell 48 GB?
EXAONE 3.5 7.8B Instruct at 8-bit runs on the RTX PRO 5000 Blackwell 48 GB with 32K of context at about 107 tokens a second.
Report VR-0K28VC4, calculated Nov 22, 2026 from published specs, not benchmarked.