Model benchmarks
Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED local LLM performance
As of October 2026, Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED runs at up to 77.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
77.9 tok/s
Average speed
77.1 tok/s
Avg PP
618.7 tok/s
Min memory
16.5 GB
Max context
65,536 tokens
Avg output / run
8,351 tokens
Avg runtime / run
1m 48s
Avg quality
80.9
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 | 78.6 | 80.9 | 83.1 |
| Agent Workflow | 80.8 | 86.7 | 92.6 |
| Code Generation | 66.0 | 70.0 | 74.0 |
| Role Play & Narrative | 83.2 | 85.5 | 87.8 |
| Research & Analysis | 79.8 | 81.2 | 82.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 9070/9070 XT/9070 GRE | OpenAI-compatible | — | 77.9 tok/s | 77.1 tok/s | 16.5 GB | 65,536 tokens | 80.9 | 2 |
Benchmark runs
All 2 Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED good for coding?
- In our benchmarks, Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED scores 70.0/100 for coding. It runs at about 77.1 tok/s, so if you want more speed, Nex-N2.5-mini-IQ3_XXS is faster (~91.4 tok/s) and still scores well for coding (81.6/100).
- Is Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED good for agentic (tool-using) tasks?
- In our benchmarks, Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED scores 86.7/100 for agentic workflows. It runs at about 77.1 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~91.6 tok/s) and still scores well for agentic workflows (89.8/100).
- How fast is Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED for local inference?
- Across 2 community benchmark runs, Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED reaches up to 77.9 tok/s and averages 77.1 tok/s, with the fastest results on AMD Radeon RX 9070/9070 XT/9070 GRE.
- How much memory does Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED need?
- The leanest observed configuration used about 16.5 GB of memory.
- Which tools have been used to run Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED?
- Benchmarks were submitted using OpenAI-compatible. Results are community-contributed and updated as new runs arrive.