Model benchmarks
cyber-tiel-coder-35b-a3b-mtp-ud local LLM performance
As of November 2026, cyber-tiel-coder-35b-a3b-mtp-ud runs at up to 35.0 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
35.0 tok/s
Average speed
31.8 tok/s
Avg PP
294.9 tok/s
Min memory
11.8 GB
Max context
32,768 tokens
Avg output / run
25,571 tokens
Avg runtime / run
14m 53s
Avg quality
78.7
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 | 78.6 | 78.7 | 78.8 |
| Agent Workflow | 83.2 | 87.0 | 90.8 |
| Code Generation | 53.3 | 63.9 | 74.4 |
| Role Play & Narrative | 69.9 | 77.7 | 85.4 |
| Research & Analysis | 84.8 | 86.3 | 87.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination cyber-tiel-coder-35b-a3b-mtp-ud has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3060 | llama.cpp | — | 35.0 tok/s | 35.0 tok/s | 29.1 GB | 32,768 tokens | 78.8 | 1 |
| NVIDIA GeForce RTX 3060 | LM Studio | IQ3_XXS | 28.6 tok/s | 28.6 tok/s | 11.8 GB | 32,768 tokens | 78.6 | 1 |
Benchmark runs
All 2 cyber-tiel-coder-35b-a3b-mtp-ud 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 good for coding?
- In our benchmarks, cyber-tiel-coder-35b-a3b-mtp-ud scores 63.9/100 for coding. It runs at about 31.8 tok/s, so if you want more speed, Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp is faster (~37.5 tok/s) and still scores well for coding (83.8/100).
- Is cyber-tiel-coder-35b-a3b-mtp-ud good for agentic (tool-using) tasks?
- In our benchmarks, cyber-tiel-coder-35b-a3b-mtp-ud scores 87.0/100 for agentic workflows. It runs at about 31.8 tok/s, so if you want more speed, swift-iq2_xs is faster (~91.5 tok/s) and still scores well for agentic workflows (91.4/100).
- How fast is cyber-tiel-coder-35b-a3b-mtp-ud for local inference?
- Across 2 community benchmark runs, cyber-tiel-coder-35b-a3b-mtp-ud reaches up to 35.0 tok/s and averages 31.8 tok/s, with the fastest results on NVIDIA GeForce RTX 3060.
- How much memory does cyber-tiel-coder-35b-a3b-mtp-ud need?
- The leanest observed configuration used about 11.8 GB of memory (quantizations tested: IQ3_XXS).
- Which tools have been used to run cyber-tiel-coder-35b-a3b-mtp-ud?
- Benchmarks were submitted using LM Studio, llama.cpp. Results are community-contributed and updated as new runs arrive.