Model comparison
LFM2.5-Queen-Opus-4.7-8B-A1B vs Qwen3-VL-8B-Instruct-abliterated-v1
These two publish different quantization sets; the table below has the exact sizes.
From the file· summed bytes, KV per layer
Side by side
| LFM2.5-Queen-Opus-4.7-8B-A1B | Qwen3-VL-8B-Instruct-abliterated-v1 | |
|---|---|---|
| Parameters | 8.5B | 8.8B |
| Architecture | lfm2moe | qwen3vl |
| Layers | 24 | — |
| Native context | 128,000 | — |
| Mixture of experts | yes, 32 experts | no |
| Quantizations published | 24 | 48 |
| Smallest quantization | 1.70 GiB | 1.97 GiB |
| Q4_K_M | — | 4.68 GiB |
| Licence | other | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | LFM2.5-Queen-Opus-4.7-8B-A1B | Qwen3-VL-8B-Instruct-abliterated-v1 | Ratio |
|---|---|---|---|
| 4,096 | 0.05 GiB | — | — |
| 8,192 | 0.09 GiB | — | — |
| 16,384 | 0.19 GiB | — | — |
| 32,768 | 0.38 GiB | — | — |
| 65,536 | 0.75 GiB | — | — |
| 131,072 | 1.50 GiB | — | — |