Model benchmarks
tiel-coder-35b local LLM performance
As of October 2026, tiel-coder-35b runs at up to 78.6 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
78.6 tok/s
Average speed
76.1 tok/s
Avg PP
924.2 tok/s
Min memory
17.2 GB
Max context
65,536 tokens
Avg output / run
5,100 tokens
Avg runtime / run
1m 19s
Avg quality
77.0
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 | 71.2 | 77.0 | 82.7 |
| Agent Workflow | 80.7 | 81.3 | 81.9 |
| Code Generation | 74.1 | 78.4 | 82.7 |
| Role Play & Narrative | 50.3 | 68.6 | 86.9 |
| Research & Analysis | 79.4 | 79.6 | 79.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination tiel-coder-35b 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 RTX A2000 12GB | llama.cpp | — | 78.6 tok/s | 76.1 tok/s | 17.2 GB | 65,536 tokens | 77.0 | 2 |
Benchmark runs
All 2 tiel-coder-35b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is tiel-coder-35b good for coding?
- In our benchmarks, tiel-coder-35b scores 78.4/100 for coding. It runs at about 76.1 tok/s, so if you want more speed, Nex-N2.5-mini-IQ3_XXS is faster (~91.4 tok/s) and still scores well for coding (81.6/100).
- Is tiel-coder-35b good for agentic (tool-using) tasks?
- In our benchmarks, tiel-coder-35b scores 81.3/100 for agentic workflows. It runs at about 76.1 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 for local inference?
- Across 2 community benchmark runs, tiel-coder-35b reaches up to 78.6 tok/s and averages 76.1 tok/s, with the fastest results on NVIDIA RTX A2000 12GB.
- How much memory does tiel-coder-35b need?
- The leanest observed configuration used about 17.2 GB of memory.
- Which tools have been used to run tiel-coder-35b?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.