llamaperf

Caphlon-2

1 report

Caphlon-2 VRAM requirements by size and quant →

How does Caphlon-2 run on your hardware?

Pick your GPU or Mac, then read the speeds people reported for Caphlon-2 on it, or estimate memory fit and speed.

Free to use. No account needed. Memory estimates and community measurements are labelled separately.

Run Caphlon-2 yourself? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance for Caphlon-2

Filter this model’s reports by setup →
One report for this model so far, so treat the figures as early. Add yours.

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Caphlon-2 27B

NVIDIA T4 16GB · PrismML llama.cpp

NVIDIA hardware
generation:
16.3 tokens/s
prompt processing (prefill):
277.9 tokens/s
quant:
PTQ1_SB (GGUF)
math

User releases Caphlon-2, a 27B model based on Qwen 3.8 27B and Ternary-Bonsai-2-27B, reporting 277.95 tok/s prompt processing (pp512) and 16.33 tok/s generation on a Tesla T4, and around 18 tok/s on an M2 MacBook Air. The 4.52 GiB (1.648 bpw) build uses PTQ1_SB ternary quantization with a trimmed 83,200-token vocabulary and trimmed FFN layers 44-61, and needs a drop-in patch for PrismML llama.cpp. Reported scores are 80.0% on GPQA-Diamond, 87.4% on Halu-270 with ITI steering (85.9% pure) and 80.0% on EN-40. A separate Caphlon-1 build (6.87 GiB, IQ2_S) runs on stock llama.cpp and Ollama.

Nov 22, 2026

Get a weekly email of new Caphlon-2 reports on any GPU.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
Caphlon-2 27B
NVIDIA T4 16GB
PTQ1_SB
PrismML llama.cpp
Not reported16.3 tokens/s