Model benchmarks
Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS local LLM performance
As of September 2026, Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS runs at up to 111.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
111.5 tok/s
Average speed
77.6 tok/s
Avg prefill
703.2 tok/s
Min memory
17.1 GB
Max context
262,144 tokens
Avg output / run
15,549 tokens
Avg runtime / run
4m 6s
Avg quality
82.4
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 | 81.8 | 82.4 | 83.1 |
| Agent Workflow | 81.0 | 86.4 | 91.8 |
| Code Generation | 75.2 | 77.0 | 78.7 |
| Role Play & Narrative | 77.2 | 83.7 | 90.2 |
| Research & Analysis | 79.4 | 82.7 | 85.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Tiel-Coder-35B-A3B-MTP-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 | — | 111.5 tok/s | 77.6 tok/s | 17.1 GB | 262,144 tokens | 82.4 | 2 |
Frequently asked questions
- Is Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS good for coding?
- In our benchmarks, Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS scores 77.0/100 for coding. It runs at about 77.6 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-MTP-UD-IQ3_XXS good for agentic (tool-using) tasks?
- In our benchmarks, Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS scores 86.4/100 for agentic workflows. It runs at about 77.6 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-Q4_K_S is faster (~165.0 tok/s) and still scores well for agentic workflows (89.3/100).
- How fast is Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS for local inference?
- Across 2 community benchmark runs, Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS reaches up to 111.5 tok/s and averages 77.6 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does Tiel-Coder-35B-A3B-MTP-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-MTP-UD-IQ3_XXS?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.