Model benchmarks
tiel-coder-35b-a3b-mtp-ud-iq4_xs local LLM performance
As of November 2026, tiel-coder-35b-a3b-mtp-ud-iq4_xs runs at up to 87.2 tok/s for local inference (best of 2 community benchmark runs across 0 GPUs).
Model size
35B
Peak speed
87.2 tok/s
Average speed
86.8 tok/s
Avg PP
828.0 tok/s
Min memory
n/a
Max context
131,072 tokens
Avg output / run
29,175 tokens
Avg runtime / run
5m 33s
Avg quality
85.1
Benchmark runs
2
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 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 | 83.3 | 85.1 | 86.8 |
| Agent Workflow | 77.2 | 81.1 | 84.9 |
| Code Generation | 78.4 | 81.6 | 84.8 |
| Role Play & Narrative | 87.9 | 88.7 | 89.5 |
| Research & Analysis | 88.2 | 89.0 | 89.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination tiel-coder-35b-a3b-mtp-ud-iq4_xs 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 GPU | llama.cpp | — | 87.2 tok/s | 86.8 tok/s | n/a | 131,072 tokens | 85.1 | 2 |
Benchmark runs
All 2 tiel-coder-35b-a3b-mtp-ud-iq4_xs runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is tiel-coder-35b-a3b-mtp-ud-iq4_xs good for coding?
- In our benchmarks, tiel-coder-35b-a3b-mtp-ud-iq4_xs scores 81.6/100 for coding. It runs at about 86.8 tok/s, so if you want more speed, ornith-1.5-35b-apex is faster (~147.2 tok/s) and still scores well for coding (83.9/100).
- Is tiel-coder-35b-a3b-mtp-ud-iq4_xs good for agentic (tool-using) tasks?
- In our benchmarks, tiel-coder-35b-a3b-mtp-ud-iq4_xs scores 81.1/100 for agentic workflows. It runs at about 86.8 tok/s, so if you want more speed, Ornith-1.5-35B-A3B-BigBang-oQ8e-mtp is faster (~102.7 tok/s) and still scores well for agentic workflows (91.1/100).
- How fast is tiel-coder-35b-a3b-mtp-ud-iq4_xs for local inference?
- Across 2 community benchmark runs, tiel-coder-35b-a3b-mtp-ud-iq4_xs reaches up to 87.2 tok/s and averages 86.8 tok/s, with the fastest results on NVIDIA GPU.
- Which tools have been used to run tiel-coder-35b-a3b-mtp-ud-iq4_xs?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.