Sarvam 105B — Hardware Requirements & GPU Compatibility
Chat
Sarvam 105B is a 106.0B-parameter open language model from sarvamai. It supports a context window of up to 131,072 tokens. At BF16 it needs about 233.27 GB of VRAM — see which GPUs and Macs can run it below.
11.1K downloads
274 likesSpecifications
- Publisher
- sarvamai
- Parameters
- 106.0B
- Architecture
- SarvamMLAForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-03-03
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Sarvam 105B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 233.3 GB | — | 212.06 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Sarvam 105B?
BF16 · 233.3 GBSarvam 105B (BF16) requires 233.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 304+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Sarvam 105B?
BF16 · 233.3 GB3 devices with unified memory can run Sarvam 105B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Sarvam 105B need?
Sarvam 105B requires 233.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 106.0B × 16 bits ÷ 8 = 212.1 GB
KV Cache + Overhead ≈ 21.2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF16233.3 GB- Can NVIDIA GeForce RTX 5090 run Sarvam 105B?
No — Sarvam 105B requires at least 233.3 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Sarvam 105B on a Mac?
Sarvam 105B requires at least 233.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Sarvam 105B locally?
Yes — Sarvam 105B can run locally on consumer hardware. At BF16 quantization it needs 233.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Sarvam 105B?
At BF16, Sarvam 105B can reach ~19 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B300 → 8000 ÷ 233.3 × 0.65 = ~22 tok/s
Estimated speed at BF16 (233.3 GB)
~22 tok/s~19 tok/s~19 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Sarvam 105B?
At BF16, the download is about 212.06 GB.
- Which GPUs can run Sarvam 105B?
No single consumer GPU has enough VRAM to run Sarvam 105B at BF16 (233.3 GB). Multi-GPU or professional hardware is required.
- Which devices can run Sarvam 105B?
4 devices with unified memory can run Sarvam 105B at BF16 (233.3 GB), including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA DGX A100 640GB, NVIDIA DGX H100. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.