LLM Name | QVikhr 3 4B Instruction |
Repository ๐ค | https://huggingface.co/Vikhrmodels/QVikhr-3-4B-Instruction |
Model Name | QVikhr-3-4B-Instruction |
Base Model(s) | |
Model Size | 4b |
Required VRAM | 8.1 GB |
Updated | 2025-08-30 |
Maintainer | Vikhrmodels |
Model Type | qwen3 |
Instruction-Based | Yes |
Model Files | |
Supported Languages | ru en |
Model Architecture | Qwen3ForCausalLM |
License | apache-2.0 |
Context Length | 40960 |
Model Max Length | 40960 |
Transformers Version | 4.52.4 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | float16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 562208 | 249 |
Qwen3 4B Instruct 2507 FP8 | 256K / 5.2 GB | 20966 | 26 |
Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 18435 | 8 |
...4B Thinking 2507 DAG Reasoning | 256K / 16.1 GB | 8937 | 4 |
Test7 | 256K / 8.1 GB | 473 | 0 |
... Instruct 2507 Gabliterated V1 | 256K / 8.1 GB | 394 | 7 |
... Instruct 2507 Gabliterated V2 | 256K / 8.1 GB | 253 | 6 |
Nyarin 4B | 256K / 8.9 GB | 41 | 2 |
NOVER1 Qwen3 4B | 256K / 8.9 GB | 100 | 2 |
...nstruct 2507 20250808 233922 0 | 256K / 8.1 GB | 91 | 5 |
๐ 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! ๐