iChancellor’s AI
← All action models
Open model

Chancellor-1 8B Instruct

Fast and light — runs anywhere

8B params64K tokensApache-2.0Launches October 10, 2026

Not released yet — every artifact below ships on launch day. Until then, the Actionfield preview simulates the experience.

About this model

Chancellor-1 8B is an Action Learning Model that distills the flagship's planning and execution policies into a package that runs on a single consumer GPU — or a laptop. It shares the same fully documented training data and the same open evaluation suite.

Distillation was done transparently: the 8B learned from its 70B sibling's published outputs on the open corpus, and the distillation set is itself released. Nothing about how the small model got its abilities is a secret.

The engineering priority was the first token, not the last benchmark point. On a mid-range consumer GPU the 8B responds in under a second, and quantized GGUF builds bring it to laptops and single-board computers at 6 GB of memory. It is the model we actually deploy — in classrooms, on field robots, and in community projects where a datacenter isn't an option.

It is also the recommended starting point for fine-tuning research: a full LoRA run fits in an afternoon on one GPU, and our released recipes reproduce our own fine-tunes exactly.

What it’s good at

  • Runs locally on 12 GB of VRAM (quantized: 6 GB)
  • Sub-second first-token latency on consumer hardware
  • Same open data audit as the 70B flagship
  • Transparent distillation — the teacher data is public
  • Ideal for fine-tuning experiments and education

Where people use it

Local-first apps with no cloud dependencyClassroom deployments and teaching labsOn-robot reasoning for field platformsWeekend-scale fine-tuning research
Method

How it was trained — in the open

01

Shared corpus

Same audited 4.1T-token recipe as the flagship, subsampled with a published curriculum for the smaller capacity.

02

Open distillation

Learned from released Chancellor-1 70B outputs; the full distillation set is downloadable.

03

Instruction tuning

The flagship's SFT set, filtered for tasks where an 8B can realistically excel — honesty over pretension.

04

Quantization QA

Every released GGUF build re-runs the full eval suite; degradation per bit-width is published, not hidden.

Evidence

Benchmarks, with context

Numbers without baselines are marketing. Every score below ships with its comparison point and its caveat.

BenchmarkThis modelReferenceNote
GradSci-QA (graduate science)54.652.3 · best open 8B peerhonest: use the 70B for frontier work
LiveEval (contamination-resistant)49.144.7 · best open 8B peeritems postdate training cutoff
First-token latency (RTX 4070)0.4 s1.9 s · 70B on same GPU**70B offloaded; 8B fits in VRAM
ToolUse-Hard66.861.0 · best open 8B peeropen tool schemas
Open artifacts

Everything ships at launch

Launches October 10, 2026. Want a note the moment they’re live? Get notified.

Model weights

safetensors · 16 GBLaunches October 10, 2026

Quantized builds

GGUF · 4/5/8-bitLaunches October 10, 2026

Fine-tuning recipes

LoRA + fullLaunches October 10, 2026

Evaluation suite

shared with 70BLaunches October 10, 2026