Benchmark result
ornith-ai/Ornith-1.5-9B-GGUF on NVIDIA GeForce RTX 4070 — 87.2 tok/s
Measured with Unsloth Studio on September 28, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
How this run compares
1st fastest of 9 runs of this model on NVIDIA GeForce RTX 4070 · median 62.3 tok/s.
sort
- 187.2tok/s58.3Unsloth Studio · Q6_K · KV f16this run
- 280.5tok/s76.9Unsloth Studio · Q4_K_M · KV q8_0
- 366.1tok/s58.7Unsloth Studio · Q4_K_M · KV f16
- 463.7tok/s54.8Unsloth Studio · IQ4_XS · KV f16
- 562.3tok/s73.6Unsloth Studio · Q6_K · KV q8_0
- 658.4tok/s63.8Unsloth Studio · Q6_K · KV q8_0
- 756.8tok/s82.5Unsloth Studio · Q6_K · KV f16
- 856.6tok/s56.2Unsloth Studio · Q6_K · KV f16
- 949.7tok/s62.2Unsloth Studio · Q6_K · KV f16
Reproduce this run
toolUnsloth Studio
modelornith-ai/Ornith-1.5-9B-GGUF (Q6_K)
context50,000
kv cachef16
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.82+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "ornith-ai/Ornith-1.5-9B-GGUF" --tool "Unsloth Studio"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.