BOTTENSOR
Bottensor — Open Research Lab
Non-player characters,
leveling up.

Bottensor is a research lab building small, specialist language models. Three open-weight models live on HuggingFace today. Architectural innovation on small models is next.

View on HuggingFaceRead the research
4
Shipped models
1.4K
HF downloads · 30d
32B
Largest model
Apache 2.0
License
Why NPC

Every model in the family starts as a non-player character — a background role in a world where frontier labs train the protagonists. The work is to level them up. Proprietary data, logic-tree reasoning, domain-specialist training. The bet is that small models, trained right, beat generalist protagonists inside their vertical. NPC is the family. Bottensor is the lab building them.

Open Research LabNPC Model FamilySmall SpecialistsQwen2.5-32BSmolLM2-1.7BUnslothQLoRAGPTQ 4-bitProcess Reward ModelsHuggingFaceOpen WeightsApache 2.0Fine-TunedOpen Research LabNPC Model FamilySmall SpecialistsQwen2.5-32BSmolLM2-1.7BUnslothQLoRAGPTQ 4-bitProcess Reward ModelsHuggingFaceOpen WeightsApache 2.0Fine-Tuned
Total HF downloads
across 8 repos · last 30 days
1.4K
NPC Fast
2 repos
697
50.2%
NPC Agent
4 repos
650
46.8%
NPC Fin
1 repo
15
1.1%
NPC Fin PRM
1 repo
26
1.9%
Open Weights

Four models shipped.
Three in research.

All open, all on HuggingFace. Weights, recipes, and evaluations are public as they land.

01
Shipped
NPC Fin
Finance · 32B

32B finance reasoning specialist. Fine-tuned on curated market examples. Weighs evidence, flags risks, delivers structured theses. Base: Qwen2.5-32B-Instruct. Method: QLoRA SFT → merged → GPTQ 4-bit. CryptoQA 93.6%.

15 downloads · 32B · QLoRA SFT · updated 15 days ago
HuggingFace →
02
Shipped
NPC Fin PRM
Alignment · 7B

7B process reward model. Verifies NPC Fin’s reasoning step by step. The alignment layer that keeps the specialist honest. Spearman 0.9234 · F1 0.8421.

26 downloads · 7B · Process RM · updated 15 days ago
HuggingFace →
03
Shipped
NPC Fast
Lightweight · 1.7B

1.7B lightweight model for routing, lookups, translation, and general-purpose tasks. Fast inference, compact footprint. Shipped in both safetensors and GGUF formats.

697 downloads · 1.7B · bf16 + GGUF · updated 16 days ago
HuggingFace →
04
Shipped
NPC Agent
Agentic · 7B

7B agentic specialist for tool use, planning, and multi-step execution. Base: Qwen2.5-7B-Instruct. Method: QLoRA SFT → merged → GPTQ 4-bit + GGUF. Shipped in safetensors, LoRA, GPTQ, and GGUF formats.

650 downloads · 7B · QLoRA SFT · updated 8 days ago
HuggingFace →
05
Research
NPC Coder
Code Generation

Production-grade code generation across Python, TypeScript, Solidity, Java. Repo-level context and tool-use.

06
Research
NPC Reason
Chain-of-Thought

Deep multi-step reasoning. Logic trees, step-by-step decomposition, verifiable chains.

07
Research
NPC Context
Long Context

Extended context for document and codebase reasoning. Target context length TBD.

Flagship Research Artifact

NPC Fin

A 32B finance specialist fine-tuned on curated market data, quantized for fast inference, and paired with a 7B process reward model that verifies reasoning step by step. Open weights, open recipes.

15 HF downloads (30d)· updated 15 days agoView on HuggingFace →
model_spec.json
ModelNPC Fin 32B
BaseQwen2.5-32B-Instruct
MethodQLoRA SFT → Merged → GPTQ 4-bit
Parameters32 billion
QuantizationGPTQ 4-bit (≈19 GB)
Training Data~32K examples · ~60M tokens
Context Length32,768 tokens
LicenseApache 2.0
Training Data Distribution
market_signal35%
finance_general25%
logic_tree20%
macro12%
cross_market8%
Open
NPC Fin 32B SFT
Fine-tune · QLoRA
15 downloads · npc-fin-32b-sft
Open
NPC Fin PRM
Process reward model · 7B
26 downloads · npc-fin-prm-7b
Open
NPC Fast
Lightweight · 1.7B
526 downloads · npc-fast-1.7b
Open
NPC Fast GGUF
GGUF quants · llama.cpp
171 downloads · npc-fast-1.7b-gguf
Open
NPC Agent
Fine-tune · QLoRA
379 downloads · npc-agentic-7b-v3
Open
NPC Agent LoRA
LoRA adapter
23 downloads · npc-agentic-7b-v3-lora
Open
NPC Agent GPTQ
GPTQ 4-bit
34 downloads · npc-agentic-7b-v3-gptq-4bit
Open
NPC Agent GGUF
GGUF quants · llama.cpp
214 downloads · npc-agentic-7b-v3-gguf
Research

What we're working on next.

Frontier labs are scaling protagonists: hundreds of billions of parameters, trained on everything, good at nothing in particular. Bottensor is betting the other direction. Small, specialist models — under 32B — trained on proprietary domain data, aligned with process reward models, and shipped as families of collaborating specialists rather than monolithic generalists. The NPC models released today are fine-tunes of open bases. The next phase is architectural: new attention patterns for domain reasoning, new training objectives that bake logic-tree discrimination into the base weights, and new data recipes that treat reasoning traces as first-class training signal. The hypothesis is that a family of small, sharp, architecturally-differentiated specialists outperforms a single large generalist inside real workflows — at a fraction of the inference cost and with weights small enough to run anywhere.

Research collaboration
Get in touch to discuss the thesis or the roadmap.
research@bottensor.xyz →
Publications

Preprints & recipes.

Open preprints on Zenodo. Each paper documents the recipe behind a shipped model — data, training, evaluation. Cited as you would any preprint.

Preprint · CC-BY-4.0
NPC Fast 1.7B: Building a Usable Small Model on a Single H100
doi.org/10.5281/zenodo.19771040Zenodo · open access
Preprint · CC-BY-4.0
Cheap PRMs: Training a Process Reward Model on a Single H100
doi.org/10.5281/zenodo.19800784Zenodo · open access
Preprint · CC-BY-4.0
NPC Fin 32B: Multi-GPU QLoRA on 12×H100
doi.org/10.5281/zenodo.19802598Zenodo · open access
Preprint · CC-BY-4.0
NPC Agentic 7B v3: Single-GPU QLoRA Recipe
doi.org/10.5281/zenodo.19954103Zenodo · open access
ORCID 0009-0000-1298-0681· Bottensor (Independent Research)· All papers CC-BY-4.0
About

A small research lab.

Bottensor is a small research lab. We build small, fast, specialized AI models for problems generalists can't solve well. The NPC Model Family is our long-term project — one model per real-world domain, shipped with open weights and open recipes.

We run the whole pipeline end-to-end: data curation, fine-tuning with QLoRA and Unsloth, quantization, and evaluation. Roughly 25% of what we do stays closed (proprietary datasets, training recipes we're still refining), and 75% ships open (weights, code, evals). That ratio will shift as the research matures.

Founded by Rama Krishna Bachu.

R
Rama Krishna Bachu
Founder · Bottensor

Building the NPC Model Family end-to-end. Data, training, evaluation, research direction. Previous: 7+ years software engineering, MS Computer Science.

Stack

Built with

End-to-end AI infrastructure — from data pipelines to production inference.

Qwen2.5-32B
Unsloth
QLoRA
vLLM
Python
PyTorch
GPTQ 4-bit
HuggingFace
OpenAI API
Next.js
TypeScript
MongoDB
RunPod
A100 / H100
Vercel