Kev 4B
- Context
- 8K
- Listed
- 2w ago
- Parameters
- 4B
- Input / 1M tokens
- $0.04
- Output / 1M tokens
- $0.00
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Jaredpalmer
- Model family
- —
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Listed on OpenRouter
- September 25, 2026
- Model ID
jaredpalmer/kev-4b- Openness
- Open weights
- License
- —
- Parameters
- 4B
- Input modalities
- text
- Output modalities
- decisions
- Modality
- text->decisions
- Native context
- 256K
- Tokenizer
- Other
- Max output tokens
- 7K
- Hugging Face
- jaredpalmer/kev-4b
- Source freshness
- Endpoints synced Oct 14, 2026, 8:18 PM UTC
Open-weight builds
Ollama variants
Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.
| Variant | Parameters | Type | Quantization | Size | Context | Input |
|---|---|---|---|---|---|---|
| kev:0.8b-mlx-bf16 | 0.8B | — | BF16 | 1.5 GB | 256K | text |
| kev:0.8b-mxfp8 | 0.8B | — | — | 1 GB | 256K | text |
| kev:4b-mlx-bf16 | 4B | — | BF16 | 8.4 GB | 256K | text |
| kev:9b-mlx-bf16 | 9B | — | BF16 | 16 GB | 256K | text |
| kev:latest | 9B | — | — | 6.7 GB | 256K | text |
| kev:27b-mlx-bf16 | 27B | — | BF16 | 51 GB | 256K | text |
| kev:27b-nvfp4 | 27B | — | — | 19 GB | 256K | text |
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| phala | 8K | $0.04 | $0.00 | — | — | 97.21% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| siliconflow/fp8 | 8K | $0.04 | $0.00 | — | — | 98.85% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.