Skip to main content
Flint is a 39.8B-parameter mixture-of-experts model from Recursive Superintelligence, Inc. (RecursiveSI), founded by Richard Socher. Only 2.5B parameters activate per token, which means it runs on a single 24 GB consumer GPU at Q4 while delivering coding-agent performance that rivals much larger models.
Last verified: 2026-10-24

​
Why Flint matters

Flint is purpose-built for agentic coding — investigating codebases, fixing bugs, implementing features, writing tests. It supports multi-turn tool use and structured tool-call grammar. The 2.5B active parameter count means it fits hardware that cannot run any other model in its performance class. Notably, Flint was built largely by its own AI research system — an early demonstration of self-improving AI (autoresearch).

​
Specs

​
Attention architecture

Flint uses a hybrid attention pattern:
  • 35 sliding-window layers (window size 513 tokens) for efficient local context
  • 14 full-attention layers with RoPE for long-range dependencies
This hybrid design keeps the KV cache small while maintaining 262K context capability.

​
Hardware fit

All 39.8B parameters must stay resident in memory — only the 2.5B active count reduces compute per token, not memory. The GGUF sizes from Unsloth:
Sweet spot: Q4_K_XL on RTX 5090. At 25.1 GB, it fits comfortably in 32 GB with room for KV cache at moderate context lengths. Q3_K_XL on a used RTX 3090 (24 GB, ~$800) is the best budget path.

​
Benchmarks

Best-in-class for MoE models under ~5B active parameters.

​
Run it

Check the Ollama library for current tags.
  • Temperature: 1.0
  • Top-p: 0.95
  • Top-k: 20
  • Min output tokens: 32,768

​
Connect it with Tokios

Once Flint is running on your hardware through any of the backends above, pair the Tokios connector to reach it as https://api.tokios.com from Claude Code, Cline, or any compatible client.
1

Pair the Tokios connector

Sign in at tokios.com/console, open the Setup tab, and click Start pairing to get a one-time claim code (TKS-XXXX-XXXX). Run the installer on the machine hosting Flint:
Linux
Then approve the device on the Setup or Connectors tab.
2

Register a deployment

In the Models tab, register flint as the upstream model id and choose a public deployment name.
3

Create an API key

In the Keys tab, click Create key. Copy the sk-tok-... key — it is shown only once.

​
Caveats

  • All 39.8B parameters stay resident. The 2.5B active count reduces compute per token, not memory. Plan for 25+ GB at Q4.
  • Knowledge cutoff is June 2026. Flint does not know about events after that date.
  • Apache 2.0 license is permissive. Commercial use is allowed with no restrictions.
  • NVFP4 variant available. NVIDIA published an FP4 quantization for Blackwell GPUs.
  • Built by AI. Flint was largely created by RecursiveSI’s own AI research system. This is an early demonstration of autoresearch.

Model fit

Calculate which quantization fits your GPU.

Choose a model by task

Compare Flint against other coding models.

RTX 50 series guide

Best consumer GPUs for running Flint.

Quickstart

Connect Flint to Tokios for remote access.