Pricing
The runtime is free. Models are one-time purchases - buy once, run on your hardware.
Free
$0
- Lean runtime (single binary, all platforms)
- lean-agent-35b (35B MoE, 3B active)
- lean-coder-80b (80B MoE, 3B active)
- All quantization variants
- OpenAI-compatible API server
Paid Models
One-time purchase
- lean-agent-122b (122B MoE, 10B active)
- lean-reason-397b (397B MoE, 17B active)
- lean-think-398b (398B afmoe, ~13B active)
- Full catalog bundle at a discount
- All quantization variants
Every model includes
- Model weights in
.lmpackformat with expert activation profiles - All quantization variants (Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0)
- Download via
lean pull - Free updates to purchased models
- Commercial use - no restrictions on deployment
Hardware requirements
All models run via expert offloading. Download sizes vary by quantization level.
lean-agent-35b
VRAM: 12 GB RAM: 16 GB Free
Q3_K_M
16.3 GB
Q4_K_M
21.4 GB
Q5_K_M
25.0 GB
Q6_K
30.0 GB
Q8_0
36.9 GB
lean-coder-80b
VRAM: 12 GB RAM: 32 GB Free
Q3_K_M
36.7 GB
Q4_K_M
48.7 GB
Q5_K_M
57.0 GB
Q6_K
65.8 GB
Q8_0
84.8 GB
lean-agent-122b
VRAM: 24 GB RAM: 32 GB Coming soon
Q3_K_M
56.6 GB
Q4_K_M
75.0 GB
Q5_K_M
87.8 GB
Q6_K
105.7 GB
Q8_0
129.9 GB
lean-reason-397b
VRAM: 48 GB RAM: 64 GB Coming soon
Q3_K_M
177.4 GB
Q4_K_M
244.1 GB
Q5_K_M
293.7 GB
Q6_K
326.6 GB
Q8_0
421.5 GB
lean-think-398b
VRAM: 48 GB RAM: 64 GB Coming soon
Q3_K_M
181.4 GB
Q4_K_M
241.9 GB
Q5_K_M
283.6 GB
Q6_K
343.2 GB
Q8_0
423.7 GB