LLM EXPLORER 61,561 MODELS INDEXED

Sarvam M 24B Q5 K M Gguf by tifin-india

By tifin-india · 66 downloads
HF Repo ↗ Copy URL

Sarvam M 24B Q5 K M Gguf is an open-source language model by tifin-india. Features: 24b LLM, VRAM: 16.8GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.18.

Base model:quantized:sarvamai/...   Base model:sarvamai/sarvam-m   Conversational   Gguf   Llama.cpp   Mistral   Q5   Q5 k m   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/tifin-india/sarvam-m-24b-q5-k-m-gguf 

Sarvam M 24B Q5 K M Gguf Parameters and Internals

LLM NameSarvam M 24B Q5 K M Gguf
Repository 🤗https://huggingface.co/tifin-india/sarvam-m-24b-q5-k-m-gguf 
Base Model(s)  Sarvam M   sarvamai/sarvam-m
Model Size24b
Required VRAM16.8 GB
Updated2026-07-21
Maintainertifin-india
Model Typemistral
Model Files  16.8 GB
GGUF QuantizationYes
Quantization Typegguf|q5|q5_k
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.51.3
Tokenizer ClassLlamaTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Sarvam M 24B Q5 K M Gguf

Best Alternatives
Context / RAM
Downloads
Likes
...nstruct 2506 Text Only Heretic128K / 47.3 GB1561
Goetia 24B V1.4128K / 47.3 GB3207
Cogidonia 24B128K / 95.3 GB251
...uau Devstral 24B Instruct V0.1128K / 47.3 GB12294
Grok Oss Apollyon 24B32K / 47.3 GB24225
...l Small 24B Instruct 2501 GGUF32K / 8.9 GB658228
Morbid Miasma 24B Mlx 8Bit128K / 25 GB402
Devstral Small 2507 Bnb 4bit128K / 14.2 GB3981
...al Small 2507 Unsloth Bnb 4bit128K / 15 GB1285
...al Small 2506 Unsloth Bnb 4bit40K / 15 GB1094
Note: green Score (e.g. "73.2") means that the model is better than tifin-india/sarvam-m-24b-q5-k-m-gguf.