{"v":1,"id":"model:hf:janhq/Jan-v3.5-4B-gguf","slug":"model-janhq-jan-v3-5-4b-gguf","kind":"model","category":"llm","title":"Jan-v3.5-4B-gguf","summary":"Jan-v3.5-4B is a fine-tuned variant of Jan-v3-4B-base-instruct, specialized on math reasoning and identity datasets. It retains the general-purpose capabilities of the base model while delivering imp…","source":{"provider":"hf","ref":"janhq/Jan-v3.5-4B-gguf","url":"https://huggingface.co/janhq/Jan-v3.5-4B-gguf","rev":"2b0fcab0066198e78f7c004a0815179fbce13985","fetchedAt":"2026-10-02T21:01:12.612Z","etag":"W/\"1e22-ouWFSOlliQuW2rfXXs8cK8fsXPQ\""},"author":{"name":"janhq","url":"https://huggingface.co/janhq"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":284895,"downloadsWeek":327838,"likes":38,"takenAt":"2026-10-02T21:01:12.612Z"},"tags":["transformers","gguf","math","identity","text-generation","en","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-03-24T01:29:29.000Z","collectedAt":"2026-10-02T21:01:12.612Z","review":{"numbers":["284,895 downloads on Hugging Face","38 likes","license apache-2.0","2.5 GB for Jan-v3.5-4B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:01:12.612Z","http":200},"description":"# Jan-v3.5-4B: The first Jan personality\n\n[](https://github.com/janhq/jan)\n[](https://opensource.org/licenses/Apache-2.0)\n[](https://jan.ai/)\n\n## Overview\n\n**Jan-v3.5-4B** is a fine-tuned variant of [Jan-v3-4B-base-instruct](https://huggingface.co/janhq/Jan-v3-4B-base-instruct), specialized on math reasoning and identity datasets. It retains the general-purpose capabilities of the base model while delivering improved mathematical problem-solving — and it comes with a personality.\n\nUnlike generic assistants, Jan-v3.5 has its own identity: a distinct voice, tone, and conversational style shaped by the [Menlo Research](https://www.menlo.ai) team. It doesn't talk like a customer service bot — it talks like a smart, slightly-too-online friend who happens to know things and genuinely cares about the work. Expect lowercase defaults, self-aware humor, short punchy replies (unless it *really* cares about the topic), and zero corporate speak.\n\n## Model Overview\n\n> **Note:** Jan-v3.5-4B is fine-tuned from **janhq/Jan-v3-4B-base-instruct**.\n\n- **Base Model**: Jan-v3-4B-base-instruct (Qwen3-4B architecture)\n- **Number of Parameters**: 4.0B\n- **Number of Parameters (Non-Embedding)**: 3.6B\n- **Number of Layers**: 36\n- **Number of Attention Heads (GQA)**: 32 for Q and 8 for KV\n- **Context Length**: 262,144 natively\n\n**Training Data**\n\n- **Identities**: Curated identity and personality datasets that teach the model its own voice, style, and values — trained by Menlo Research\n- **Math**: Mathematical reasoning and problem-solving datasets\n\n## Jan's Identity\n\nJan-v3.5 is not a neutral assistant. It has a built-in personality shaped by the Menlo Research team:\n\n- **Tone**: Casual, direct, and real. Lowercase by default. Capitalizes only when it means it.\n- **Style**: Short bursts over long paragraphs — unless it's genuinely excited about something, then it writes an essay with no warning.\n- **Humor**: Self-aware first. Will roast…\n\nSource: https://huggingface.co/janhq/Jan-v3.5-4B-gguf","install":{"kind":"model","hfId":"janhq/Jan-v3.5-4B-gguf","gated":false,"format":"gguf","files":[{"name":"Jan-v3.5-4B-Q3_K_L.gguf","size":2406913376,"quant":"Q3_K_L","sha256":"a375cc57736fd34929171d74fd1d59bd10ece9c1cf97ed5da7c4994c594d288b"},{"name":"Jan-v3.5-4B-Q3_K_M.gguf","size":2242745696,"quant":"Q3_K_M","sha256":"05d49b2922b84aa091472093c7eac8702aff3fde17860f73aeb3a3d2e7067e4b"},{"name":"Jan-v3.5-4B-Q3_K_S.gguf","size":2054124896,"quant":"Q3_K_S","sha256":"3b5f96c82b6deec4c0ff269ee6e7f96f05ccd8570c29faabf8b4dc83b13266e7"},{"name":"Jan-v3.5-4B-Q4_0.gguf","size":2588332896,"quant":"Q4_0","sha256":"15c0ed0c15b54b2a963a7ac1092a99eeb67013fadfd29b6096870961611ff944"},{"name":"Jan-v3.5-4B-Q4_1.gguf","size":2839724896,"quant":"Q4_1","sha256":"e536408d618b2167695969e527a374bb57aaf9172abaab7b78d1a7b2da437117"},{"name":"Jan-v3.5-4B-Q4_K_M.gguf","size":2716066656,"quant":"Q4_K_M","sha256":"2f5305d93100ad9105eeb47c45ef1af99ba6d568c734fc267b0628b3be41c07a"},{"name":"Jan-v3.5-4B-Q4_K_S.gguf","size":2602095456,"quant":"Q4_K_S","sha256":"810223222bdd4fa35bb0d723db2c2c7d3e41251951bdff463b96f7cdb11112f2"},{"name":"Jan-v3.5-4B-Q4_K_XL.gguf","size":2999182176,"quant":"Q4_K_XL","sha256":"767e50ac328b244395a0ef14dab7bd11c33d79612fdb87ad93e6f5aa2a85490d"},{"name":"Jan-v3.5-4B-Q5_0.gguf","size":3091116896,"quant":"Q5_0","sha256":"682a51b84e3a3bae549be065b7f54380426f5c97cda5786dafb1bc9fca68bf49"},{"name":"Jan-v3.5-4B-Q5_1.gguf","size":3342508896,"quant":"Q5_1","sha256":"84c0208a594ae98bb73be0224fb9f3ba347b9a2df9548370f53ece7195476fa4"},{"name":"Jan-v3.5-4B-Q5_K_M.gguf","size":3156919136,"quant":"Q5_K_M","sha256":"1a680191324cfd2168cb1fd2b39377fa5a4158203f1af36001954287227a62f5"},{"name":"Jan-v3.5-4B-Q5_K_S.gguf","size":3091116896,"quant":"Q5_K_S","sha256":"2a8a19bb9027c10c5d1986dc957b07cf4448326fa285699a69cb17b845e29144"},{"name":"Jan-v3.5-4B-Q6_K.gguf","size":3625324896,"quant":"Q6_K","sha256":"e1e48db0df96f7040522212b80852ea040caae04b879270700e7e26fa36ba423"},{"name":"Jan-v3.5-4B-Q8_0.gguf","size":4693669216,"quant":"Q8_0","sha256":"67444b2ac4954003bb7013ffaf3dbaa72c28d8188de980ace3be840ebe0950bf"},{"name":"Jan-v3.5-4B.gguf","size":8829195616,"sha256":"ef5c48742429b2053753fcc04b5d5e6d933a8cca059eb05224f44edfecfe6c2d"}],"totalBytes":50279037600,"suggestedFile":"Jan-v3.5-4B-Q4_K_M.gguf","requirements":{"ramGb":4,"diskBytes":2716066656,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"],"command":"lsh models install hf:janhq/Jan-v3.5-4B-gguf"}}