Model benchmarks
Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL local LLM performance
As of September 2026, Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL runs at up to 98.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
98.2 tok/s
Average speed
98.1 tok/s
Avg prefill
1352.6 tok/s
Min memory
17.1 GB
Max context
262,144 tokens
Avg output / run
14,555 tokens
Avg runtime / run
2m 35s
Avg quality
84.8
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 | 84.1 | 84.8 | 85.6 |
| Agent Workflow | 81.4 | 87.3 | 93.2 |
| Code Generation | 73.5 | 79.3 | 85.1 |
| Role Play & Narrative | 86.1 | 86.7 | 87.3 |
| Research & Analysis | 82.2 | 86.1 | 89.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL 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 | Q2_K | 98.2 tok/s | 98.1 tok/s | 17.1 GB | 262,144 tokens | 84.8 | 2 |
Frequently asked questions
- Is Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL good for coding?
- In our benchmarks, Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL scores 79.3/100 for coding. It runs at about 98.1 tok/s, so if you want more speed, Qwen3.6-35B-A3B-Q4_K_XL is faster (~156.9 tok/s) and still scores well for coding (82.2/100).
- Is Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL scores 87.3/100 for agentic workflows. It runs at about 98.1 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-Q2_K_XL for local inference?
- Across 2 community benchmark runs, Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL reaches up to 98.2 tok/s and averages 98.1 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL need?
- The leanest observed configuration used about 17.1 GB of memory (quantizations tested: Q2_K).
- Which tools have been used to run Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.