Ornstein3.6-27B-MTP-NSC-ACE-SABER
1recorded run
32.9best tok/s
1verified
What the Ornstein3.6-27B-MTP-NSC-ACE-SABER numbers mean
The fastest verified result on our board is 32.9 output tok/s on an RTX 3090 at Q4_K_M with a 262144-token context. That is about 30.4 ms per generated token — 500 tokens takes roughly 15.2 seconds. Prompt processing on the same record runs at 98.9 tok/s, so a 2,000-token prompt is read in about 20.2 seconds. Peak VRAM was measured at 22.0 GB.
How much VRAM does Ornstein3.6-27B-MTP-NSC-ACE-SABER need?
Ornstein3.6-27B-MTP-NSC-ACE-SABER has 27.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.
| Quantisation | Estimated VRAM | Smallest card that fits |
|---|---|---|
| Q4_K_M (4-bit) | 18.3 GB | 24 GB |
| Q8_0 (8-bit) | 33.8 GB | 48 GB |
| FP16 (16-bit) | 62.9 GB | 80 GB |
Fastest GPUs for this model (best tok/s)
- RTX 309032.9
Models with a similar footprint
| Model | Params | Q4_K_M weights |
|---|---|---|
| gemma-4-26B-A4B-it | 27B | 15.2 GB |
| gemma-4-26B-A4B-it-qat | 27B | 15.2 GB |
| gemma-4-26B-A4B-it-ultra-uncensored-heretic | 27B | 15.2 GB |
| Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP | 27B | 15.2 GB |
| Qwen3.8-27B-MTP | 27B | 15.2 GB |
| Ternary Bonsai 2 27B | 27B | 15.2 GB |