Model comparison
Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning 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
| Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning | Qwen3-VL-8B-Instruct-abliterated-v1 | |
|---|---|---|
| Parameters | 12.2B | 8.8B |
| Architecture | llama | qwen3vl |
| Layers | 40 | — |
| Native context | 1,024,000 | — |
| Mixture of experts | no | no |
| Quantizations published | 24 | 48 |
| Smallest quantization | 2.79 GiB | 1.97 GiB |
| Q4_K_M | — | 4.68 GiB |
| Licence | — | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning | Qwen3-VL-8B-Instruct-abliterated-v1 | Ratio |
|---|---|---|---|
| 4,096 | 0.63 GiB | — | — |
| 8,192 | 1.25 GiB | — | — |
| 16,384 | 2.50 GiB | — | — |
| 32,768 | 5.00 GiB | — | — |
| 65,536 | 10.00 GiB | — | — |
| 131,072 | 20.00 GiB | — | — |