Translategemma Tok is an open-source language model by zhoucantd. Features: 4b LLM, VRAM: 0.2GB, LLM Explorer Score: 0.26.
Arxiv:1910.09700 Base model:adapter:google/tran... Base model:google/translategem... Conversational Llama-factory Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/zhoucantd/translategemma-tok
Translategemma Tok Benchmarks
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)
Translategemma Tok Parameters and Internals
| LLM Name | Translategemma Tok |
| Repository 🤗 | https://huggingface.co/zhoucantd/translategemma-tok |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 0.2 GB |
| Updated | 2026-03-29 |
| Maintainer | zhoucantd |
| Model Files | |
| Model Architecture | AutoModel |
| Is Biased | none |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | 29.self_attn.k_proj|down_proj|30.self_attn.v_proj|27.self_attn.k_proj|language_model.layers.14.self_attn.v_proj|language_model.layers.24.self_attn.k_proj|language_model.layers.7.self_attn.k_proj|language_model.layers.22.self_attn.k_proj|language_model.layers.14.self_attn.q_proj|28.self_attn.v_proj|30.self_attn.k_proj|31.self_attn.v_proj|language_model.layers.3.self_attn.k_proj|32.self_attn.v_proj|28.self_attn.k_proj|language_model.layers.1.self_attn.v_proj|29.self_attn.v_proj|language_model.layers.26.self_attn.q_proj|language_model.layers.10.self_attn.q_proj|29.self_attn.q_proj|language_model.layers.24.self_attn.v_proj|language_model.layers.16.self_attn.k_proj|language_model.layers.15.self_attn.k_proj|language_model.layers.6.self_attn.q_proj|28.self_attn.q_proj|language_model.layers.12.self_attn.q_proj|language_model.layers.25.self_attn.q_proj|30.self_attn.q_proj|language_model.layers.17.self_attn.v_proj|language_model.layers.25.self_attn.v_proj|language_model.layers.19.self_attn.v_proj|language_model.layers.4.self_attn.k_proj|27.self_attn.q_proj|language_model.layers.3.self_attn.q_proj|language_model.layers.1.self_attn.q_proj|language_model.layers.23.self_attn.v_proj|33.self_attn.k_proj|language_model.layers.19.self_attn.q_proj|language_model.layers.5.self_attn.q_proj|language_model.layers.0.self_attn.k_proj|language_model.layers.26.self_attn.k_proj|27.self_attn.v_proj|language_model.layers.13.self_attn.k_proj|language_model.layers.11.self_attn.k_proj|language_model.layers.24.self_attn.q_proj|language_model.layers.20.self_attn.k_proj|32.self_attn.k_proj|31.self_attn.k_proj|language_model.layers.12.self_attn.v_proj|language_model.layers.9.self_attn.k_proj|gate_proj|language_model.layers.12.self_attn.k_proj|language_model.layers.2.self_attn.q_proj|language_model.layers.6.self_attn.v_proj|language_model.layers.23.self_attn.k_proj|language_model.layers.21.self_attn.k_proj|language_model.layers.15.self_attn.q_proj|language_model.layers.7.self_attn.v_proj|language_model.layers.15.self_attn.v_proj|language_model.layers.20.self_attn.v_proj|language_model.layers.9.self_attn.v_proj|language_model.layers.0.self_attn.q_proj|language_model.layers.2.self_attn.k_proj|language_model.layers.0.self_attn.v_proj|33.self_attn.v_proj|language_model.layers.18.self_attn.q_proj|language_model.layers.21.self_attn.q_proj|language_model.layers.13.self_attn.q_proj|language_model.layers.10.self_attn.k_proj|33.self_attn.q_proj|language_model.layers.1.self_attn.k_proj|language_model.layers.20.self_attn.q_proj|language_model.layers.16.self_attn.q_proj|language_model.layers.18.self_attn.k_proj|language_model.layers.21.self_attn.v_proj|language_model.layers.3.self_attn.v_proj|language_model.layers.13.self_attn.v_proj|language_model.layers.17.self_attn.q_proj|language_model.layers.7.self_attn.q_proj|language_model.layers.10.self_attn.v_proj|language_model.layers.23.self_attn.q_proj|language_model.layers.9.self_attn.q_proj|language_model.layers.18.self_attn.v_proj|o_proj|language_model.layers.8.self_attn.q_proj|language_model.layers.14.self_attn.k_proj|language_model.layers.2.self_attn.v_proj|language_model.layers.8.self_attn.v_proj|language_model.layers.22.self_attn.q_proj|32.self_attn.q_proj|language_model.layers.19.self_attn.k_proj|31.self_attn.q_proj|language_model.layers.6.self_attn.k_proj|language_model.layers.4.self_attn.q_proj|language_model.layers.17.self_attn.k_proj|language_model.layers.22.self_attn.v_proj|language_model.layers.11.self_attn.v_proj|language_model.layers.5.self_attn.v_proj|language_model.layers.25.self_attn.k_proj|up_proj|language_model.layers.16.self_attn.v_proj|language_model.layers.4.self_attn.v_proj|language_model.layers.5.self_attn.k_proj|language_model.layers.11.self_attn.q_proj|language_model.layers.26.self_attn.v_proj|language_model.layers.8.self_attn.k_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 32 |
Best Alternatives to Translategemma Tok
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 4B Chunky | 0K / 0.3 GB | 19 | 0 |
| Gemma3 Konkani | 0K / 0 GB | 119 | 5 |
| Gemma3 Konkani 4B | 0K / 0 GB | 119 | 5 |
| AYA Mistral7B Instruct TR 4B | 0K / 0.3 GB | 0 | 6 |
| ...emeter LongCoT Qwen3 1.7B GGUF | 0K / 0.8 GB | 839 | 2 |
| II Search 4B GGUF | 0K / 1.7 GB | 751 | 5 |
| ...upyter Agent Qwen3 4B AIO GGUF | 0K / 1.7 GB | 327 | 4 |
| Qwen3 4B Abliterated F32 GGUFs | 0K / 1.7 GB | 397 | 2 |
| Basically Human 4B F32 GGUF | 0K / 1.7 GB | 45 | 2 |
| Chinda Qwen3 4B F32 GGUF | 0K / 1.7 GB | 170 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than zhoucantd/translategemma-tok .
Rank the Translategemma Tok 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? 53053 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