Model benchmarks
Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL local LLM performance
As of September 2026, Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL runs at up to 36.1 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
36.1 tok/s
Average speed
35.1 tok/s
Avg PP
222.3 tok/s
Min memory
n/a
Max context
85,248 tokens
Avg output / run
28,008 tokens
Avg runtime / run
13m
Avg quality
85.5
Benchmark runs
3
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 3 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 | 83.4 | 85.5 | 87.4 |
| Agent Workflow | 89.4 | 90.5 | 91.4 |
| Code Generation | 80.3 | 83.3 | 86.4 |
| Role Play & Narrative | 77.5 | 82.6 | 89.9 |
| Research & Analysis | 84.8 | 85.6 | 86.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Tiel-Coder-35B-A3B-MTP-UD-Q6_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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 XT | llama.cpp | Q6_K | 36.1 tok/s | 35.1 tok/s | n/a | 85,248 tokens | 85.5 | 3 |
Benchmark runs
All 3 Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL 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-Q6_K_XL good for coding?
- In our benchmarks, Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL scores 83.3/100 for coding. It runs at about 35.1 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL scores 90.5/100 for agentic workflows. It runs at about 35.1 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL for local inference?
- Across 3 community benchmark runs, Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL reaches up to 36.1 tok/s and averages 35.1 tok/s, with the fastest results on AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 XT.
- Which tools have been used to run Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.