Falcon 2 11B
Falcon 2 11B is an open-weights language model from TII, released May 9, 2024. It has 11B parameters (dense). On the Epoch Capabilities Index it scores 99.3, rank 216 of 256 rated models.
Check it against your own PC →
Lab
TII
Released
May 9, 2024
Weights
Open restricted use
Parameters
11B dense
Context
–
Price / M tokens
–
Epoch ECI
99.3 #216
Can you run Falcon 2 11B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q4_K_M, split GPU / CPU, roughly 6 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 | Runs, slowly | Q4_K_M (very good) | 5.2 GB | 4.5 GB | ~6 |
| 8 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 7.2 GB | 4.8 GB | ~5 |
| 12 GB VRAM | Runs on GPU | Q5_K_M (excellent) | 10.8 GB | – | ~27 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 12.0 GB | – | ~32 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 12.0 GB | – | ~59 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 12.0 GB | – | ~110 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 44.5% |
Links
Models with a similar score
Gemma 7B · Mistral 7B v0.1 · Yi-9B · Qwen-14B · LLaMA-65B · DeepSeek-Coder-V2-Lite-Base · Nemotron-4 15B · internlm-20b