Model benchmarks
Tiel-Coder-35B-A3B.APEX-I-NanoPlus local LLM performance
As of October 2026, Tiel-Coder-35B-A3B.APEX-I-NanoPlus runs at up to 84.9 tok/s for local inference (best of 3 community benchmark runs across 2 GPUs).
Model size
35B
Peak speed
84.9 tok/s
Average speed
62.1 tok/s
Avg PP
905.3 tok/s
Min memory
14.2 GB
Max context
262,144 tokens
Avg output / run
29,943 tokens
Avg runtime / run
13m 58s
Avg quality
75.6
Benchmark runs
3
GPUs tested
2
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 | 68.4 | 75.6 | 79.9 |
| Agent Workflow | 72.1 | 77.1 | 81.2 |
| Code Generation | 26.3 | 59.4 | 79.6 |
| Role Play & Narrative | 75.1 | 81.4 | 86.2 |
| Research & Analysis | 82.9 | 84.3 | 86.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination Tiel-Coder-35B-A3B.APEX-I-NanoPlus 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 5060 | llama.cpp | — | 84.9 tok/s | 83.2 tok/s | 18.8 GB | 262,144 tokens | 73.6 | 2 |
| NVIDIA GeForce RTX 4050 Laptop GPU | llama.cpp | — | 19.9 tok/s | 19.9 tok/s | 14.2 GB | 65,536 tokens | 79.6 | 1 |
Benchmark runs
All 3 Tiel-Coder-35B-A3B.APEX-I-NanoPlus runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Tiel-Coder-35B-A3B.APEX-I-NanoPlus good for coding?
- In our benchmarks, Tiel-Coder-35B-A3B.APEX-I-NanoPlus scores 59.4/100 for coding. It runs at about 62.1 tok/s, so if you want more speed, ornith-1.5-35b-a3b-apex-i-quality is faster (~75.9 tok/s) and still scores well for coding (82.9/100).
- Is Tiel-Coder-35B-A3B.APEX-I-NanoPlus good for agentic (tool-using) tasks?
- In our benchmarks, Tiel-Coder-35B-A3B.APEX-I-NanoPlus scores 77.1/100 for agentic workflows. It runs at about 62.1 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 Tiel-Coder-35B-A3B.APEX-I-NanoPlus for local inference?
- Across 3 community benchmark runs, Tiel-Coder-35B-A3B.APEX-I-NanoPlus reaches up to 84.9 tok/s and averages 62.1 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does Tiel-Coder-35B-A3B.APEX-I-NanoPlus need?
- The leanest observed configuration used about 14.2 GB of memory.
- Which tools have been used to run Tiel-Coder-35B-A3B.APEX-I-NanoPlus?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.