Benchmark result
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP on NVIDIA GeForce RTX 4070 — 81.5 tok/s
Measured with Unsloth Studio on October 24, 2026.
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
2nd fastest of 5 runs of this model on NVIDIA GeForce RTX 4070 · median 76.3 tok/s.
sort
- 182.3tok/s82.6Unsloth Studio · UD-IQ4_XS · KV q4_0
- 281.5tok/s83.9Unsloth Studio · UD-IQ4_XS · KV q4_0this run
- 376.3tok/s86.9Unsloth Studio · UD-IQ4_XS · KV q4_0
- 476.1tok/s83.5Unsloth Studio · UD-IQ4_XS · KV q4_0
- 553.9tok/s87.4Unsloth Studio · UD-IQ4_XS · KV q4_0
Reproduce this run
toolUnsloth Studio
modelpeculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP (UD-IQ4_XS)
context65,536
kv cacheq4_0
thinkingon
effortmedium
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.97+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP" --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.