s-batman/ornith-1.0-35b-nvfp4
Ornith 1.0 35B NVFP4 (MTP GGUF)
Throughput
8.7t/s@ 192k
Engine
llama.cpp
Parameters
35B
Released
2026-06-26
Benchmarked
2026-07-08
Throughput uses bench v2: we prefill to ~75% of the max context window, then measure decode under a simulated agent workload — not a few-token micro-benchmark.
Context ladder
Throughput at each benched context window.
| Context | KV | Throughput |
|---|---|---|
| @ 192k peak golden | — | 8.7t/s |
| @ 196k peak golden | q8_0 | 8.7t/s |
| @ 256k | q8_0 | 6.9t/s |
Benchmark runs
Recorded inference benchmark sessions for this model's profile (single run).
| Date | Profile | Method | Avg | Session t/s | Range | Fill | Tool |
|---|---|---|---|---|---|---|---|
| 2026-07-08latest | s-batman-ornith-1-0-35b-nvfp4-mtp-llama-2 | bench-agent-v2v2.0 | 8.7t/s | — | — | ~132,711 | ok |
| golden 196k/q8_0 @ 8.7 tok/s — fill~133k — bench-agent-v2 — tool_ok=True | |||||||
Capabilities
generalmoeggufllamacpp
Why we run it
Community MTP GGUF variant — bench v2 golden workflow 2026-07-08.
Bench notes
golden 196k/q8_0 @ 8.7 tok/s — fill~133k — bench-agent-v2 — tool_ok=True