Model benchmarks
Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL local LLM performance
As of September 2026, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL runs at up to 54.8 tok/s for local inference (best of 3 community benchmark runs across 0 GPUs).
Model size
35B
Peak speed
54.8 tok/s
Average speed
53.9 tok/s
Avg PP
1554.5 tok/s
Min memory
n/a
Max context
100,000 tokens
Avg output / run
29,583 tokens
Avg runtime / run
8m 50s
Avg quality
84.5
Benchmark runs
3
GPUs tested
0
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 | 83.5 | 84.5 | 85.2 |
| Agent Workflow | 82.7 | 86.0 | 89.9 |
| Code Generation | 77.5 | 80.6 | 82.7 |
| Role Play & Narrative | 82.8 | 84.8 | 87.2 |
| Research & Analysis | 84.0 | 86.8 | 88.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL 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 |
|---|---|---|---|---|---|---|---|---|
| CPU only | llama.cpp | Q5_K | 54.8 tok/s | 53.9 tok/s | n/a | 100,000 tokens | 84.5 | 3 |
Benchmark runs
All 3 Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL 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-Q5_K_XL good for coding?
- In our benchmarks, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL scores 80.6/100 for coding. It runs at about 53.9 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~96.3 tok/s) and still scores well for coding (83.4/100).
- Is Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL scores 86.0/100 for agentic workflows. It runs at about 53.9 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-Q5_K_XL for local inference?
- Across 3 community benchmark runs, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL reaches up to 54.8 tok/s and averages 53.9 tok/s.
- Which tools have been used to run Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.