Model benchmarks
IFM/K2-Horizon-7B-GGUF local LLM performance
As of October 2026, IFM/K2-Horizon-7B-GGUF runs at up to 71.9 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
7B
Peak speed
71.9 tok/s
Average speed
69.5 tok/s
Avg PP
2961.8 tok/s
Min memory
9.6 GB
Max context
65,536 tokens
Avg output / run
11,720 tokens
Avg runtime / run
2m 52s
Avg quality
68.1
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 | 66.1 | 68.1 | 70.6 |
| Agent Workflow | 81.7 | 86.9 | 90.3 |
| Code Generation | 14.1 | 25.8 | 34.9 |
| Role Play & Narrative | 62.3 | 77.4 | 87.9 |
| Research & Analysis | 79.9 | 82.4 | 85.0 |
Performance by hardware and tool
Every hardware/tool/quantization combination IFM/K2-Horizon-7B-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 | Q4_K_M | 71.9 tok/s | 69.5 tok/s | 9.6 GB | 65,536 tokens | 68.1 | 3 |
Benchmark runs
All 3 IFM/K2-Horizon-7B-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is IFM/K2-Horizon-7B-GGUF good for coding?
- In our benchmarks, IFM/K2-Horizon-7B-GGUF scores 25.8/100 for coding. It runs at about 69.5 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 IFM/K2-Horizon-7B-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, IFM/K2-Horizon-7B-GGUF scores 86.9/100 for agentic workflows. It runs at about 69.5 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is IFM/K2-Horizon-7B-GGUF for local inference?
- Across 3 community benchmark runs, IFM/K2-Horizon-7B-GGUF reaches up to 71.9 tok/s and averages 69.5 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does IFM/K2-Horizon-7B-GGUF need?
- The leanest observed configuration used about 9.6 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run IFM/K2-Horizon-7B-GGUF?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.