Sarvam 30B BF16 — Hardware Requirements & GPU Compatibility
Chat
Sarvam 30B BF16 is a 32.2B-parameter open language model from abhinand. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 19.63 GB of VRAM — see which GPUs and Macs can run it below.
171 downloads
3 likesSpecifications
- Publisher
- abhinand
- Parameters
- 32.2B
- Architecture
- SarvamMoEForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-03-08
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Sarvam 30B BF16 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q4_K_M | 4.80 | 19.6 GB | 22.1 GB | 19.29 GB | 4-bit medium quantization — most popular sweet spot |
Which GPUs Can Run Sarvam 30B BF16?
Q4_K_M · 19.6 GBSarvam 30B BF16 (Q4_K_M) requires 19.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 131K context window can add up to 2.5 GB, bringing total usage to 22.1 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Sarvam 30B BF16?
Q4_K_M · 19.6 GB21 devices with unified memory can run Sarvam 30B BF16, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Sarvam 30B BF16 need?
Sarvam 30B BF16 requires 19.6 GB of VRAM at Q4_K_M. Full 131K context adds up to 2.5 GB (22.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.2B × 4.8 bits ÷ 8 = 19.3 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.8 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M19.6 GBQ4_K_M + full context22.1 GB- Can I run Sarvam 30B BF16 on a Mac?
Sarvam 30B BF16 requires at least 19.6 GB at Q4_K_M, 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 30B BF16 locally?
Yes — Sarvam 30B BF16 can run locally on consumer hardware. At Q4_K_M quantization it needs 19.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Sarvam 30B BF16?
At Q4_K_M, Sarvam 30B BF16 can reach ~149 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~33 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 19.6 × 0.55 = ~149 tok/s
Estimated speed at Q4_K_M (19.6 GB)
~149 tok/s~33 tok/s~111 tok/s~92 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Sarvam 30B BF16?
At Q4_K_M, the download is about 19.29 GB.
- Which GPUs can run Sarvam 30B BF16?
6 consumer GPUs can run Sarvam 30B BF16 at Q4_K_M (19.6 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Sarvam 30B BF16?
21 devices with unified memory can run Sarvam 30B BF16 at Q4_K_M (19.6 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.