Store › model › LLM
Jan-v3.5-4B-gguf
by janhq · source Hugging Face · updated 2026-03-24
apache-2.02.5 GB~4 GB RAMsource aliveunlabeled
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…
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:janhq/Jan-v3.5-4B-gguf and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/janhq/Jan-v3.5-4B-gguf
- License: apache-2.0
- Requirements: about 4 GB of RAM, 2.5 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
transformersggufmathidentitytext-generationenendpoints_compatibleconversational
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
Numbers as of 2026-10-02 21:01 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
Jan-v3.5-4B-Q3_K_L.gguf | Q3_K_L | 2.2 GB |
Jan-v3.5-4B-Q3_K_M.gguf | Q3_K_M | 2.1 GB |
Jan-v3.5-4B-Q3_K_S.gguf | Q3_K_S | 1.9 GB |
Jan-v3.5-4B-Q4_0.gguf | Q4_0 | 2.4 GB |
Jan-v3.5-4B-Q4_1.gguf | Q4_1 | 2.6 GB |
Jan-v3.5-4B-Q4_K_M.gguf | Q4_K_M | 2.5 GB |
Jan-v3.5-4B-Q4_K_S.gguf | Q4_K_S | 2.4 GB |
Jan-v3.5-4B-Q4_K_XL.gguf | Q4_K_XL | 2.8 GB |
Jan-v3.5-4B-Q5_0.gguf | Q5_0 | 2.9 GB |
Jan-v3.5-4B-Q5_1.gguf | Q5_1 | 3.1 GB |
Jan-v3.5-4B-Q5_K_M.gguf | Q5_K_M | 2.9 GB |
Jan-v3.5-4B-Q5_K_S.gguf | Q5_K_S | 2.9 GB |
Jan-v3.5-4B-Q6_K.gguf | Q6_K | 3.4 GB |
Jan-v3.5-4B-Q8_0.gguf | Q8_0 | 4.4 GB |
Jan-v3.5-4B.gguf | 8.2 GB |
From the source README
Jan-v3.5-4B: The first Jan personality
Overview
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 improved mathematical problem-solving — and it comes with a personality.
Unlike generic assistants, Jan-v3.5 has its own identity: a distinct voice, tone, and conversational style shaped by the Menlo Research 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.
Model Overview
> Note: Jan-v3.5-4B is fine-tuned from janhq/Jan-v3-4B-base-instruct.
- Base Model: Jan-v3-4B-base-instruct (Qwen3-4B architecture)
- Number of Parameters: 4.0B
- Number of Parameters (Non-Embedding): 3.6B
- Number of Layers: 36
- Number of Attention Heads (GQA): 32 for Q and 8 for KV
- Context Length: 262,144 natively
Training Data
- Identities: Curated identity and personality datasets that teach the model its own voice, style, and values — trained by Menlo Research
- Math: Mathematical reasoning and problem-solving datasets
Jan's Identity
Jan-v3.5 is not a neutral assistant. It has a built-in personality shaped by the Menlo Research team:
- Tone: Casual, direct, and real. Lowercase by default. Capitalizes only when it means it.
- Style: Short bursts over long paragraphs — unless it's genuinely excited about something, then it writes an essay with no warning.
- Humor: Self-aware first. Will roast…
Card id model:hf:janhq/Jan-v3.5-4B-gguf · collected 2026-10-02 21:01 UTC · JSON