SILMA Kashif 2B Instruct V1.0 is an open-source language model by silma-ai. Features: 2b LLM, VRAM: 5.2GB, Context: 12K, License: gemma, Instruction-Based, LLM Explorer Score: 0.22.
Ar Conversational Deploy:azure En Endpoints compatible Gemma2 Instruct Model-index Qa Rag Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/silma-ai/SILMA-Kashif-2B-Instruct-v1.0
SILMA Kashif 2B Instruct V1.0 Benchmarks
MMLU Pro: 13.98
GPQA: 2.68
MUSR: 8.27
BBH: 12.84
IFEval: 11.81 vs 88 (so35)-86.6%
MATH Lvl 5: 1.13
LLME Score: 0.21745
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
SILMA Kashif 2B Instruct V1.0 Parameters and Internals
| LLM Name | SILMA Kashif 2B Instruct V1.0 |
| Repository 🤗 | https://huggingface.co/silma-ai/SILMA-Kashif-2B-Instruct-v1.0 |
| Model Size | 2b |
| Required VRAM | 5.2 GB |
| Updated | 2026-04-24 |
| Maintainer | silma-ai |
| Model Type | gemma2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ar en |
| Model Architecture | Gemma2ForCausalLM |
| License | gemma |
| Context Length | 12288 |
| Model Max Length | 12288 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to SILMA Kashif 2B Instruct V1.0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma2b Nirf Lookup 2025 | 8K / 5.2 GB | 5 | 0 |
| GaMS 2B Instruct | 8K / 5.2 GB | 1346 | 2 |
| Gemma 2 2B Opus Instruct | 8K / 5.2 GB | 13 | 2 |
| Gemma 2 2B It Coding | 8K / 5.2 GB | 153 | 0 |
| Gemma 2 2B It Instruction | 8K / 5.2 GB | 84 | 0 |
| Gemma 2 2b Coding | 8K / 5.2 GB | 12 | 0 |
| Gemma 2 2b Instruction | 8K / 5.2 GB | 184 | 0 |
| Gemma 2 2B Neogenesis Ita | 8K / 5.2 GB | 1350 | 6 |
| Code Trans Gemma 2 2B Sft | 8K / 5.2 GB | 7 | 0 |
| Gemma 2 2B Instruct | 8K / 5.2 GB | 5 | 0 |
Rank the SILMA Kashif 2B Instruct V1.0 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53232 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a