sarvamai/sarvam-105b-gguf

!!! This is the GGUF version of Sarvam-105B !!!

Download the original weights here!

Index

1. Introduction
2. Architecture
3. Benchmarks
   • Knowledge & Coding
   • Reasoning & Math
   • Agentic
4. Inference
5. Footnote
6. Citation

Introduction

Sarvam-105B is an advanced Mixture-of-Experts (MoE) model with 10.3B active parameters, designed for superior performance across a wide range of complex tasks. It is highly optimized for complex reasoning, with particular strength in agentic tasks, mathematics, and coding.

Sarvam-105B is a top-tier performer, consistently matching or surpassing several major closed-source models and staying within a narrow margin of frontier models across diverse reasoning and agentic benchmarks. It demonstrates exceptional agentic and reasoning capabilities in real-world applications such as web search and technical troubleshooting.

A major focus during training was the Indian context and languages, resulting in state-of-the-art performance across 22 Indian languages for its model size.

Sarvam-105B is open-sourced under the Apache License. For more details, see our blog.

Architecture

The 105B model adopts an MLA-style attention stack with decoupled QK head dimensions (q_head_dim=192 split into RoPE and noPE components, v_head_dim=128) and a large head_dim of 576, enabling higher representational bandwidth per head while keeping the hidden size at 4096. This approach improves attention expressivity and long-context extrapolation (via YaRN scaling with a factor of 40 and 128K context). It has an intermediate_size (16384) and moe_intermediate_size (2048), combined with top-8 routing over 128 experts, which increases per-token active capacity while keeping activation cost manageable. The model has one shared expert, a routed scaling factor of 2.5, and auxiliary-loss-free router balancing.

Benchmarks

Knowledge & Coding Reasoning & Math Agentic

See footnote for evaluation details.

Inference

Clone and build

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp && cmake -B build && cmake --build build --config Release -j

Download the model (all shards)

huggingface-cli download sarvam/sarvam-105-gguf --local-dir sarvam-105b-gguf

Run interactive chat

./build/bin/llama-cli \
  -m sarvam-105b-gguf/sarvam-105b-Q4_K_M.gguf-00001-of-00009.gguf \
  -c 4096 \
  -n 512 \
  -p "You are a helpful assistant." \
  --conversation

OpenAI-compatible API server

./build/bin/llama-server \
  -m sarvam-105b-gguf/sarvam-105b-Q4_K_M.gguf-00001-of-00009.gguf \
  -c 4096 \
  --host 0.0.0.0 \
  --port 8080

Then query it:

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.8,
    "max_tokens": 512
  }'

Note:

• Use -ngl -1 to enable GPU acceleration (if available)
• Omit -ngl to run on CPU

Footnote

• General settings: All benchmarks are evaluated with a maximum context length of 65,536 tokens.
• Reasoning & Math benchmarks (Math500, MMLU, MMLU Pro, GPQA Diamond, AIME 25, Beyond AIME, HMMT): Evaluated with temperature=1.0, top_p=1.0, max_new_tokens=65536.
• Coding & Knowledge benchmarks (Live Code Bench v6, Arena Hard v2, IF Eval): Evaluated with temperature=1.0, top_p=1.0, max_new_tokens=65536.
• Writing Bench: Responses generated using official Writing-Bench parameters: temperature=0.7, top_p=0.8, top_k=20, max_length=16000. Scoring performed using the official Writing-Bench critic model with: temperature=1.0, top_p=0.95, max_length=2048.
• Agentic benchmarks (BrowseComp, SWE Bench Verified, τ² Bench): Evaluated with temperature=0.5, top_p=1.0, max_new_tokens=32768.

Citation

@misc{sarvam_sovereign_models,
  title        = {Introducing Sarvam's Sovereign Models},
  author       = {{Sarvam Foundation Models Team}},
  year         = {2026},
  howpublished = {\url{https://www.sarvam.ai/blogs/sarvam-30b-105b}},
  note         = {Accessed: 2026-03-03}
}