Model benchmarks
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL local LLM performance
As of September 2026, peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL runs at up to 25.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
25.9 tok/s
Average speed
19.6 tok/s
Avg PP
123.6 tok/s
Min memory
n/a
Max context
131,072 tokens
Avg output / run
15,176 tokens
Avg runtime / run
18m 47s
Avg quality
71.2
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 | 60.6 | 71.2 | 81.8 |
| Agent Workflow | 71.5 | 81.3 | 91.0 |
| Code Generation | 3.3 | 33.3 | 63.3 |
| Role Play & Narrative | 87.8 | 90.4 | 93.0 |
| Research & Analysis | 74.4 | 79.8 | 85.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_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 2060 | llama.cpp | Q4_K | 25.9 tok/s | 25.9 tok/s | n/a | 131,072 tokens | 83.0 | 1 |
| NVIDIA GeForce RTX 2060 | OpenAI-compatible | Q4_K | 13.2 tok/s | 13.2 tok/s | n/a | 8,192 tokens | 59.4 | 1 |
Benchmark runs
All 2 peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL good for coding?
- In our benchmarks, peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL scores 33.3/100 for coding. It runs at about 19.6 tok/s, so if you want more speed, Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF-Q6_K is faster (~34.2 tok/s) and still scores well for coding (85.9/100).
- Is peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL scores 81.3/100 for agentic workflows. It runs at about 19.6 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 peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL for local inference?
- Across 2 community benchmark runs, peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL reaches up to 25.9 tok/s and averages 19.6 tok/s, with the fastest results on NVIDIA GeForce RTX 2060.
- Which tools have been used to run peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF:Q4_K_XL?
- Benchmarks were submitted using OpenAI-compatible, llama.cpp. Results are community-contributed and updated as new runs arrive.