Model comparison
Poe-8B-GLM5-Opus4.6-Sonnet4.5-Kimi-Grok-Gemini-3-pro-preview-HERETIC vs HyperCLOVAX-SEED-Text-Instruct-1.5B
At Q4_K_M, HyperCLOVAX-SEED-Text-Instruct-1.5B is the smaller download — 1,133,974,368 bytes against 5,027,785,824.
From the file· summed bytes, KV per layer
Side by side
| Poe-8B-GLM5-Opus4.6-Sonnet4.5-Kimi-Grok-Gemini-3-pro-preview-HERETIC | HyperCLOVAX-SEED-Text-Instruct-1.5B | |
|---|---|---|
| Parameters | 8.8B | 1.6B |
| Architecture | qwen3vl | llama |
| Layers | 36 | — |
| Native context | 262,144 | — |
| Mixture of experts | no | no |
| Quantizations published | 60 | 1 |
| Smallest quantization | 1.97 GiB | 1.06 GiB |
| Q4_K_M | 4.68 GiB | 1.06 GiB |
| Licence | apache-2.0 | other |
KV cache by context
the term that decides long-context viability
| Context | Poe-8B-GLM5-Opus4.6-Sonnet4.5-Kimi-Grok-Gemini-3-pro-preview-HERETIC | HyperCLOVAX-SEED-Text-Instruct-1.5B | Ratio |
|---|---|---|---|
| 4,096 | 0.56 GiB | — | — |
| 8,192 | 1.13 GiB | — | — |
| 16,384 | 2.25 GiB | — | — |
| 32,768 | 4.50 GiB | — | — |
| 65,536 | 9.00 GiB | — | — |
| 131,072 | 18.00 GiB | — | — |