OpenModelsHQ

sarvam-m

Sarvam AILLMDenseApache-2.0

sarvam-m is an open-weight language model from Sarvam AI with 23.6B parameters. At 4-bit it needs about 17 GB of memory, so the smallest current device that fits it is the Arc Pro B60.

Overview

Estimated memory at 4-bit
17GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
23.6B
Dense
Context window
32K
32,768 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Sarvam AI
Released
20 May 2025
Parameters
23.6B
Type
Language
Context
32,768 tokens
License
Apache-2.0
HF downloads, 30 days
4,694
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
sarvam-m needs about 17 GB at 4-bit, 29 GB at 8-bit and 53.3 GB at 16-bit. At 4-bit it fits GeForce RTX 5090, DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q417 GB
Q829 GB
BF1653.3 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 17 GBFits 47%Arc Pro B6024 GB memory
8-bit (Q8)≈ 29 GBFits 81%L40S48 GB memory
16-bit (BF16)≈ 53.3 GBToo big 148%A100 80GB SXM80 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

mlx-community/sarvam-m-8bitCheck your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

lmstudio-community/sarvam-m-GGUFFind compatible hardware

Through an API

No hosted API found.

MLX on Apple SiliconView repository
mlx_lm.generate --model mlx-community/sarvam-m-8bit \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf lmstudio-community/sarvam-m-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.

More about this model

Frequently asked questions

How much memory does sarvam-m need? At an 8k context, about 17 GB at 4-bit, 29 GB at 8-bit and 53.3 GB at 16-bit (BF16). A longer context needs more.

Can I run sarvam-m on a Mac? The smallest current Mac that fits the 4-bit estimate of 17 GB is the Mac mini M6 (32GB). An MLX build is available: mlx-community/sarvam-m-8bit.

Does the full context fit? sarvam-m supports up to 32,768 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, MLX repository, GGUF repository.