Skip to content
localmodel.run

Text model · Sarvam

SSarvam-105B requirements

Sarvam family · 105B params (Mixture-of-Experts, 10.3B active) · released Mar 2026. Minimum to run at Q4_K_M: Apple M4 Max (128GB).

LicenseApache-2.0· Commercial OK↓ 18.7K/mo♥ 275on HuggingFace
Q4_K_M
64.2 GB
Q8_0
-
Total @ Q4 (4k)
~67.5 GB
Context
128 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K44 GB est
Q3_K_M51.3 GB est
Q4_K_M (default)64.2 GB
Q5_K_M74.8 GB est
Q6_K86.1 GB est
Q8_0111.6 GB est
FP16210 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

llama.cpp
$ llama-cli -hf sarvamai/sarvam-105b-gguf:Q4_K_M
LM Studio
$ lms get sarvamai/sarvam-105b-gguf

Which devices can run Sarvam-105B?

FAQ

How much VRAM or RAM does Sarvam-105B need?

At Q4_K_M, Sarvam-105B needs about 67.5 GB (weights ~64.2 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~114.9 GB.

Can Sarvam-105B run on a laptop?

Sarvam-105B is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.

Is Sarvam-105B cheaper to run because it is a MoE model?

It is faster, not lighter. Sarvam-105B activates only 10.3B of 105B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 105B.

Can I use Sarvam-105B commercially?

Yes. Sarvam-105B is licensed Apache-2.0, which permits commercial use.

MoE with 128 experts, top-8 routing plus one shared expert, 10.3B active params. Released 2026-03 under Apache 2.0. Q4_K_M 64.2GB confirmed by summing the 9 shards in the official GGUF repo. Server-class; no Q8_0 GGUF exists.

Sources

Memory figures are estimates. See methodology.