text model · Sarvam · Windows
S Can I run Sarvam-105B on Nvidia GeForce RTX 4070 (12GB)?
No. Sarvam-105B needs ~67.5 GB even at Q4_K_M, but Nvidia GeForce RTX 4070 (12GB) only has ~11 GB usable.
Needs ~67.5 GB even at Q4_K_M, but only ~11 GB is usable.
- Q4_K_M needed
- ~67.5 GB
- Usable on device
- ~11 GB
- Device memory
- 12 GB
How to run it
On Windows use LM Studio (Best GUI on Windows, auto-detects CUDA/Vulkan backends.). AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 105B (MoE, 10.3B active)
- Q4_K_M size
- 64.2 GB
- Context
- 128k
- Memory
- 12 GB vram
- Usable for weights
- ~11 GB
- Best runtime
- Ollama (CUDA) / vLLM (Linux)
What you can run instead
Run Sarvam-105B on other hardware
FAQ
Can Nvidia GeForce RTX 4070 (12GB) run Sarvam-105B?
No. Sarvam-105B needs ~67.5 GB even at Q4_K_M, but Nvidia GeForce RTX 4070 (12GB) only has ~11 GB usable.
How much memory does Sarvam-105B need?
Nvidia GeForce RTX 4070 (12GB) does not have enough memory. At Q4_K_M the weights are ~64.2 GB; with KV cache and runtime overhead, budget ~67.5 GB at a 4k context. It is a Mixture-of-Experts model (105B total / 10.3B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Sarvam-105B on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Sources
Memory figures are estimates. See methodology.