Model
Model explorer
Sarvam-1 (2B)
OPENSarvam AI · Sarvam family · released Oct 24, 2024
India's first from-scratch open foundation model; 2B params trained on 4T tokens with a low-fertility tokenizer for 10 Indic languages plus English; base text-completion model, not chat-tuned.
ReasoningCodingVisionFunction callingTool useAgentic
129.0
Elo · rank #376
Parameters
2B
Active params
2B (dense)
Context
8K tokens
Architecture
2B dense transformer with custom Indic-optimized tokenizer
License
Sarvam Non-Commercial License
Languages
11+
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
best: Llama 3.1 405B · 96.9%
best: OpenAI o3 · 92.9%
best: this model · 90.6%
Run it locally
VRAM @ Q4
2 GB
VRAM @ FP16
5 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF Q4
Resources
API price weights · each benchmark row carries its own source badge (see methodology)