Model benchmarks
Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL local LLM performance
As of October 2026, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL runs at up to 36.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
36.2 tok/s
Average speed
36.1 tok/s
Avg PP
483.9 tok/s
Min memory
16.2 GB
Max context
65,536 tokens
Avg output / run
20,284 tokens
Avg runtime / run
9m 17s
Avg quality
84.5
Benchmark runs
2
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 2 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 | 82.8 | 84.5 | 86.2 |
| Agent Workflow | 86.5 | 87.9 | 89.2 |
| Code Generation | 79.3 | 82.2 | 85.1 |
| Role Play & Narrative | 81.9 | 82.4 | 83.0 |
| Research & Analysis | 83.6 | 85.5 | 87.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4060 Ti | llama.cpp | Q3_K | 36.2 tok/s | 36.1 tok/s | 16.2 GB | 65,536 tokens | 84.5 | 2 |
Benchmark runs
All 2 Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_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-Q3_K_XL good for coding?
- In our benchmarks, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL scores 82.2/100 for coding. It runs at about 36.1 tok/s, so if you want more speed, nvidia/Qwen3.8-27B-NVFP4 is faster (~63.3 tok/s) and still scores well for coding (82.7/100).
- Is Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL scores 87.9/100 for agentic workflows. It runs at about 36.1 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL for local inference?
- Across 2 community benchmark runs, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL reaches up to 36.2 tok/s and averages 36.1 tok/s, with the fastest results on NVIDIA GeForce RTX 4060 Ti.
- How much memory does Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL need?
- The leanest observed configuration used about 16.2 GB of memory (quantizations tested: Q3_K).
- Which tools have been used to run Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.