Model benchmarks
tiel-coder-35b-a3b-ud-q4_k_xl local LLM performance
As of November 2026, tiel-coder-35b-a3b-ud-q4_k_xl runs at up to 108.7 tok/s for local inference (best of 2 community benchmark runs across 2 GPUs).
Model size
35B
Peak speed
108.7 tok/s
Average speed
81.4 tok/s
Avg PP
434.0 tok/s
Min memory
11.2 GB
Max context
131,072 tokens
Avg output / run
32,799 tokens
Avg runtime / run
8m 7s
Avg quality
76.8
Benchmark runs
2
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 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 | 69.6 | 76.8 | 84.0 |
| Agent Workflow | 20.5 | 53.9 | 87.3 |
| Code Generation | 80.4 | 81.8 | 83.2 |
| Role Play & Narrative | 79.9 | 84.9 | 89.8 |
| Research & Analysis | 84.6 | 86.5 | 88.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination tiel-coder-35b-a3b-ud-q4_k_xl 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 GeForce RTX 5060 | PolyStrata | Q4_K | 108.7 tok/s | 108.7 tok/s | n/a | 131,072 tokens | 84.8 | 1 |
| NVIDIA GeForce RTX 3070 Ti | Polystrata | Q4_K | 54.0 tok/s | 54.0 tok/s | 11.2 GB | 65,536 tokens | 68.8 | 1 |
Benchmark runs
All 2 tiel-coder-35b-a3b-ud-q4_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-ud-q4_k_xl good for coding?
- In our benchmarks, tiel-coder-35b-a3b-ud-q4_k_xl scores 81.8/100 for coding. It runs at about 81.4 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e is faster (~97.4 tok/s) and still scores well for coding (80.9/100).
- Is tiel-coder-35b-a3b-ud-q4_k_xl good for agentic (tool-using) tasks?
- In our benchmarks, tiel-coder-35b-a3b-ud-q4_k_xl scores 53.9/100 for agentic workflows. It runs at about 81.4 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~98.3 tok/s) and still scores well for agentic workflows (89.9/100).
- How fast is tiel-coder-35b-a3b-ud-q4_k_xl for local inference?
- Across 2 community benchmark runs, tiel-coder-35b-a3b-ud-q4_k_xl reaches up to 108.7 tok/s and averages 81.4 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does tiel-coder-35b-a3b-ud-q4_k_xl need?
- The leanest observed configuration used about 11.2 GB of memory (quantizations tested: Q4_K).
- Which tools have been used to run tiel-coder-35b-a3b-ud-q4_k_xl?
- Benchmarks were submitted using PolyStrata, Polystrata. Results are community-contributed and updated as new runs arrive.