LLM EXPLORER 64,561 MODELS INDEXED

Jervis V1 by LoNebula

By LoNebula · 32 downloads
HF Repo ↗ Copy URL

Jervis V1 is an open-source language model by LoNebula. Features: 8b LLM, VRAM: 8.6GB, Context: 40K, License: apache-2.0.

  4-bit   Assistant Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-8b   Bilingual   Bitsandbytes   Conversational   En   Endpoints compatible   English   Ja   Japanese   Qlora   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoNebula/jervis-v1 

Jervis V1 Parameters and Internals

LLM NameJervis V1
Repository 🤗https://huggingface.co/LoNebula/jervis-v1 
Base Model(s)  Qwen3 8B   Qwen/Qwen3-8B
Model Size8b
Required VRAM8.6 GB
Updated2026-10-17
MaintainerLoNebula
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.6 GB: 2-of-2
Supported Languagesja en
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.57.6
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Jervis V1

Best Alternatives
Context / RAM
Downloads
Likes
PaCoRe 8B320K / 1.2 GB5448
RLVR 8B 0926320K / 1.2 GB638
...n3 8B 320K Context 10X Massive320K / 16.4 GB200
...r Of Horror Jan V1 256K Ctx 8B256K / 16.1 GB333
... BIG Jan Horror V1 256K Ctx 8B256K / 16.1 GB440
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB950
...wen3 8B 192K Context 6X Larger192K / 16.4 GB550
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB17622931082
...1 Qwen3 8B ArliAI RpR V4 Small128K / 16.4 GB1821
...Qwen3 8B NVFP4 W4A16 PreTensor128K / 0.9 GB4633
Note: green Score (e.g. "73.2") means that the model is better than LoNebula/jervis-v1.