Model benchmarks
peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF local LLM performance
As of October 2026, peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF runs at up to 95.5 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
4B
Peak speed
95.5 tok/s
Average speed
91.2 tok/s
Avg PP
3773.3 tok/s
Min memory
6.7 GB
Max context
131,072 tokens
Avg output / run
75,730 tokens
Avg runtime / run
15m
Avg quality
69.6
Benchmark runs
3
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 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 | 66.4 | 69.6 | 71.6 |
| Agent Workflow | 74.3 | 79.6 | 87.2 |
| Code Generation | 56.8 | 61.9 | 65.9 |
| Role Play & Narrative | 62.1 | 67.1 | 71.1 |
| Research & Analysis | 65.6 | 69.8 | 72.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4070 | Unsloth Studio | Q6_K_XL | 95.5 tok/s | 91.2 tok/s | 6.7 GB | 131,072 tokens | 69.6 | 3 |
Benchmark runs
All 3 peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF good for coding?
- In our benchmarks, peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF scores 61.9/100 for coding. It runs at about 91.2 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e is faster (~107.9 tok/s) and still scores well for coding (81.5/100).
- Is peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF scores 79.6/100 for agentic workflows. It runs at about 91.2 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~116.8 tok/s) and still scores well for agentic workflows (88.4/100).
- How fast is peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF for local inference?
- Across 3 community benchmark runs, peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF reaches up to 95.5 tok/s and averages 91.2 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF need?
- The leanest observed configuration used about 6.7 GB of memory (quantizations tested: Q6_K_XL).
- Which tools have been used to run peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.