Model benchmarks
Tiel-Coder-35B-A3B-UD-IQ3_XXS local LLM performance
As of September 2026, Tiel-Coder-35B-A3B-UD-IQ3_XXS runs at up to 93.0 tok/s for local inference (best of 4 community benchmark runs across 2 GPUs).
Model size
35B
Peak speed
93.0 tok/s
Average speed
66.2 tok/s
Avg PP
720.5 tok/s
Min memory
17.1 GB
Max context
131.072 tokens
Avg output / run
9.375 tokens
Avg runtime / run
2m 22s
Avg quality
74.5
Benchmark runs
4
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 4 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 | 64.7 | 74.5 | 80.1 |
| Agent Workflow | 64.8 | 73.9 | 81.3 |
| Code Generation | 60.7 | 70.5 | 79.6 |
| Role Play & Narrative | 53.7 | 75.3 | 86.7 |
| Research & Analysis | 72.9 | 78.3 | 83.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination Tiel-Coder-35B-A3B-UD-IQ3_XXS has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5060 | llama.cpp | — | 93.0 tok/s | 93.0 tok/s | 17.1 GB | 131.072 tokens | 80.3 | 1 |
| Tesla P100-PCIE-16GB | llama.cpp | — | 57.7 tok/s | 57.2 tok/s | 17.1 GB | 65.536 tokens | 72.6 | 3 |
Benchmark runs
All 4 Tiel-Coder-35B-A3B-UD-IQ3_XXS runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Tiel-Coder-35B-A3B-UD-IQ3_XXS good for coding?
- In our benchmarks, Tiel-Coder-35B-A3B-UD-IQ3_XXS scores 70.5/100 for coding. It runs at about 66.2 tok/s, so if you want more speed, unsloth/Qwen3.8-27B-GGUF:IQ3_S is faster (~104.3 tok/s) and still scores well for coding (83.0/100).
- Is Tiel-Coder-35B-A3B-UD-IQ3_XXS good for agentic (tool-using) tasks?
- In our benchmarks, Tiel-Coder-35B-A3B-UD-IQ3_XXS scores 73.9/100 for agentic workflows. It runs at about 66.2 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS is faster (~102.1 tok/s) and still scores well for agentic workflows (88.7/100).
- How fast is Tiel-Coder-35B-A3B-UD-IQ3_XXS for local inference?
- Across 4 community benchmark runs, Tiel-Coder-35B-A3B-UD-IQ3_XXS reaches up to 93.0 tok/s and averages 66.2 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does Tiel-Coder-35B-A3B-UD-IQ3_XXS need?
- The leanest observed configuration used about 17.1 GB of memory.
- Which tools have been used to run Tiel-Coder-35B-A3B-UD-IQ3_XXS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.