Model benchmarks
tiel-coder-35b-a3b local LLM performance
As of October 2026, tiel-coder-35b-a3b runs at up to 55.1 tok/s for local inference (best of 3 community benchmark runs across 2 GPUs).
Model size
35B
Peak speed
55.1 tok/s
Average speed
37.5 tok/s
Avg PP
577.5 tok/s
Min memory
31.0 GB
Max context
262,144 tokens
Avg output / run
19,291 tokens
Avg runtime / run
9m 37s
Avg quality
85.1
Benchmark runs
3
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 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 | 83.6 | 85.1 | 86.2 |
| Agent Workflow | 88.7 | 91.0 | 93.1 |
| Code Generation | 80.4 | 81.6 | 82.6 |
| Role Play & Narrative | 79.3 | 83.5 | 90.4 |
| Research & Analysis | 80.5 | 84.3 | 87.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination tiel-coder-35b-a3b 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 7900 XTX | LM Studio | — | 55.1 tok/s | 55.1 tok/s | 31.0 GB | 80,000 tokens | 83.4 | 1 |
| AMD Radeon RX 9070/9070 XT/9070 GRE | LM Studio | — | 28.8 tok/s | 28.6 tok/s | n/a | 262,144 tokens | 86.0 | 2 |
Benchmark runs
All 3 tiel-coder-35b-a3b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is tiel-coder-35b-a3b good for coding?
- In our benchmarks, tiel-coder-35b-a3b scores 81.6/100 for coding. It runs at about 37.5 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 good for agentic (tool-using) tasks?
- In our benchmarks, tiel-coder-35b-a3b scores 91.0/100 for agentic workflows. It runs at about 37.5 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 for local inference?
- Across 3 community benchmark runs, tiel-coder-35b-a3b reaches up to 55.1 tok/s and averages 37.5 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does tiel-coder-35b-a3b need?
- The leanest observed configuration used about 31.0 GB of memory.
- Which tools have been used to run tiel-coder-35b-a3b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.