Model benchmarks
Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS local LLM performance
As of September 2026, Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS runs at up to 39.4 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
39.4 tok/s
Average speed
38.3 tok/s
Avg PP
384.0 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
5,910 tokens
Avg runtime / run
2m 20s
Avg quality
74.3
Benchmark runs
3
GPUs tested
1
Quality by task
Average LLM-judged quality (0–100) with the run-to-run spread shown as a P5–P95 band, overall and for each benchmark task, across all 3 runs. The low and high columns show how much the judge’s score varies between runs, and need at least two runs to display.
| Task | P5 (low) | Avg | P95 (high) |
|---|---|---|---|
| Overall | 73.3 | 74.3 | 75.1 |
| Agent Workflow | 64.7 | 75.4 | 81.8 |
| Code Generation | 53.0 | 61.6 | 72.6 |
| Role Play & Narrative | 79.7 | 81.6 | 84.6 |
| Research & Analysis | 78.5 | 78.8 | 79.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Tesla P100-PCIE-16GB | llama.cpp | — | 39.4 tok/s | 38.3 tok/s | n/a | 65,536 tokens | 74.3 | 3 |
Benchmark runs
All 3 Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS good for coding?
- In our benchmarks, Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS scores 61.6/100 for coding. It runs at about 38.3 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS good for agentic (tool-using) tasks?
- In our benchmarks, Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS scores 75.4/100 for agentic workflows. It runs at about 38.3 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS for local inference?
- Across 3 community benchmark runs, Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS reaches up to 39.4 tok/s and averages 38.3 tok/s, with the fastest results on Tesla P100-PCIE-16GB.
- Which tools have been used to run Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ4_XS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.