Model comparison
LFM2-350M-Extract vs Qwen2.5-0.5B-Instruct
At Q4_K_M, LFM2-350M-Extract is the smaller download — 229,310,080 bytes against 397,807,936.
From the file· summed bytes, KV per layer
Side by side
| LFM2-350M-Extract | Qwen2.5-0.5B-Instruct | |
|---|---|---|
| Parameters | 354M | 494M |
| Architecture | lfm2 | qwen2 |
| Layers | 16 | 24 |
| Native context | 128,000 | 32,768 |
| Mixture of experts | no | no |
| Quantizations published | 29 | 32 |
| Smallest quantization | 0.13 GiB | 0.31 GiB |
| Q4_K_M | 0.21 GiB | 0.37 GiB |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | LFM2-350M-Extract | Qwen2.5-0.5B-Instruct | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | 0.05 GiB | 1.00× |
| 8,192 | 0.09 GiB | 0.09 GiB | 1.00× |
| 16,384 | 0.19 GiB | 0.19 GiB | 1.00× |
| 32,768 | 0.38 GiB | 0.38 GiB | 1.00× |
| 65,536 | 0.75 GiB | 0.75 GiB | 1.00× |
| 131,072 | 1.50 GiB | 1.50 GiB | 1.00× |