LBS 27B
LBS 27B is an open-weights language model from inclusionAI, released October 26, 2026. It has 27B parameters (dense). The context window is 256K tokens.
Check it against your own PC →
Lab
inclusionAI
Released
October 26, 2026
Weights
Open apache-2.0
Parameters
27B dense
Context
256K
Price / M tokens
–
Epoch ECI
not yet rated
Can you run LBS 27B locally?
The smallest common GPU it runs on is 8 GB of VRAM (with 32 GB of RAM): IQ3_XXS, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Very slow | IQ3_XXS (noticeable loss) | 5.2 GB | 6.8 GB | ~4 |
| 8 GB VRAM | Runs, slowly | IQ3_XXS (noticeable loss) | 7.2 GB | 4.8 GB | ~5 |
| 12 GB VRAM | Runs, slowly | Q3_K_M (okay) | 11.2 GB | 3.7 GB | ~6 |
| 16 GB VRAM | Runs on GPU | Q3_K_M (okay) | 14.9 GB | – | ~22 |
| 24 GB VRAM | Runs on GPU | Q5_K_M (excellent) | 20.9 GB | – | ~28 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 23.8 GB | – | ~46 |
Ready-made quantizations on Hugging Face: bartowski/LBS-27B-GGUF · mradermacher/LBS-27B-GGUF
Benchmark results
Epoch AI has not published results for LBS 27B yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: inclusionAI/LBS-27B
More from inclusionAI
Ling 3.1 flash 1019 · Ling 3.0 flash Sante · Ling 3.0 tiny · Ling-1T · Ring-1T