Tev1 4B Experimental
- Context
- 33K
- Released
- 3w 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
- Togethercomputer
- Model family
- —
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- September 22, 2026
- Model ID
togethercomputer/tev1-4b-experimental- Openness
- Open weights
- License
- —
- Parameters
- 4B
- Input modalities
- text
- Output modalities
- decisions
- Modality
- text->decisions
- Native context
- 256K
- Tokenizer
- Qwen3
- Max output tokens
- 8
- Hugging Face
- togethercomputer/Tev1-4B-experimental
- Source freshness
- Endpoints synced Oct 15, 2026, 1:11 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 |
|---|---|---|---|---|---|---|
| tev1:0.8b-bf16 | 0.8B | — | BF16 | 1.5 GB | 256K | text |
| tev1:0.8b-mlx-bf16 | 0.8B | — | BF16 | 1.5 GB | 256K | text |
| tev1:0.8b-q8_0 | 0.8B | — | Q8_0 | 812 MB | 256K | text |
| tev1:0.8b | 0.8B | — | — | 797 MB | 256K | text |
| tev1:0.8b-mxfp8 | 0.8B | — | — | 797 MB | 256K | text |
| tev1:4b-bf16 | 4B | — | BF16 | 8.4 GB | 256K | text |
| tev1:4b-mlx-bf16 | 4B | — | BF16 | 8.4 GB | 256K | text |
| tev1:4b-q4_K_M | 4B | — | Q4_K_M | 2.7 GB | 256K | text |
| tev1:4b-q8_0 | 4B | — | Q8_0 | 4.5 GB | 256K | text |
| tev1:4b-mxfp8 | 4B | — | — | 4.4 GB | 256K | text |
| tev1:4b-nvfp4 | 4B | — | — | 3.1 GB | 256K | text |
| tev1:latest | 4B | — | — | 4.4 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 |
|---|---|---|---|---|---|---|---|---|
| together | 33K | $0.04 | $0.00 | — | — | 82.23% | 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.