Model benchmarks
cyber-frost-3.8-ps local LLM performance
As of November 2026, cyber-frost-3.8-ps runs at up to 29.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
29.9 tok/s
Average speed
27.0 tok/s
Avg PP
195.9 tok/s
Min memory
97.0 GB
Max context
65,536 tokens
Avg output / run
70,788 tokens
Avg runtime / run
43m 53s
Avg quality
83.7
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 | 83.4 | 83.7 | 84.1 |
| Agent Workflow | 86.4 | 88.8 | 91.2 |
| Code Generation | 74.0 | 75.4 | 76.8 |
| Role Play & Narrative | 83.6 | 86.0 | 88.3 |
| Research & Analysis | 84.7 | 84.8 | 85.0 |
Performance by hardware and tool
Every hardware/tool/quantization combination cyber-frost-3.8-ps 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XTX | Strata | — | 29.9 tok/s | 27.0 tok/s | 97.0 GB | 65,536 tokens | 83.7 | 2 |
Benchmark runs
All 2 cyber-frost-3.8-ps runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is cyber-frost-3.8-ps good for coding?
- In our benchmarks, cyber-frost-3.8-ps scores 75.4/100 for coding. It runs at about 27.0 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 cyber-frost-3.8-ps good for agentic (tool-using) tasks?
- In our benchmarks, cyber-frost-3.8-ps scores 88.8/100 for agentic workflows. It runs at about 27.0 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 cyber-frost-3.8-ps for local inference?
- Across 2 community benchmark runs, cyber-frost-3.8-ps reaches up to 29.9 tok/s and averages 27.0 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does cyber-frost-3.8-ps need?
- The leanest observed configuration used about 97.0 GB of memory.
- Which tools have been used to run cyber-frost-3.8-ps?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.