flint
Flint is Recursive’s mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token. It is designed to investigate codebases, fix bugs, implement features, and write tests.
Params
39.8 B
Context
262,144
Downloads 30d
2 K
Likes
695
Download history
tracking started — chart appears after 7 days of snapshots (2 recorded)2 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 79.6 GB | 94.0 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 79.6 GB | 279.0 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/flint
{
"hf_id": "RecursiveSI/flint",
"params_b": 39.79,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 1904,
"vram_estimates": [
{ "quant": "bf16", "gb": 94.0 }
],
"updated_at": "2026-10-22T06:00:04Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24Free
input / 1M
Free
output / 1M
—
cached input / 1M
Free
1M in + 1M out
:free variant
Free in · Free out
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- Providers
- —
- Cheapest provider
- —
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✗ Prompt caching
Specifications
- Architecture
- FlintForCausalLM
- Parameters
- 39.8 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 150,144
- Layers / heads
- 49 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-21
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-23
Compare with any text-generation model