The story so far
Weights, every dated article, and repo commits on one rail.
5 repo commits since the weights landed
Teal is the weights (2026-09-23), grey ticks are repo commits.
Models › Tev1-experimental family
Tev1-4B-experimental
togethercomputer Not declared out 32 days ago
4.66B parameters, text in, text out, 256K tokens of context. 1 provider serves it from $0.042 per million input tokens.
Verified 2026-10-25 Rank #4591 in Decision models · score 50.2 method v1 Sources 3 Downloads 30d 4.5k · #553 of 619 tracked
Changed this week: 1 new provider: Together AI.2026-10-23
Do people use it?4.5kdownloads, 30 days#553 of 619 we track · below the median+1 likes, downloads −12% this week37 likesHugging Face2026-10-24
Where to run it
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | Together AI | $0.042 | $0 | 32K | — | Oct 25 |
Where it's used
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; 6 quantized builds for local use.
- As a service1Together AI
- On own hardware6quantized builds
- Built on22 fine-tunes · 0 adapters · 0 merges
- In apps9Hugging Face Spaces
Top Spaces running it: multimodalart/jev-decision-index ♥ 802
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 16 GB card at INT4
About 2.8 GB at INT4, 5.6 GB at FP8, 11 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
What people built on it
8 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
8 derivatives on the Hub, most of them quantized
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
What the card says
2 cited sentences
Summary generated, cited
Tev1-4B-experimental is a 4.66B parameter decision model developed by Together AI.[1][2] This supervised fine-tune of Qwen/Qwen3.5-4B is designed to select one option from a structured state, question, and list of choices.[3][4]
- parameters human
- “experimental 4B decision model from Together AI”
- base models
- “trained to choose one option from a structured state, que…”
Generated 2026-10-07 15:17 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Use-case evidence
7 use cases
What it is good at 7 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
- Classify and make typed decisionsstructuraldecision-model estimate p=1.00tag: decision-modeldecision catalog
- Run on a laptop or phonestructuraldecision-model estimate p=0.82name: 4Bfits: single-gpu
- Call tools and APIsstructuralchat template: <tool_call>tool calling at 1 provider
- Chat and follow instructionsstructuraltag: conversationalchat template present
- Understand images and videostructuraltag: image-text-to-textconfig: vision_config
- Reason through hard problemsstructuralchat template: <think>
- Read long documentsstructuralconfig: 262,144 context
Facts
20 fields
Listed in Decision models · LLMs
Facts
- Tev1-4B-experimental has 4.66B parameters. (safetensors metadata, observed 2026-10-24)
- Context length is 262,144 tokens (256K). (config.json max_position_embeddings, observed 2026-10-24)
- License: Not declared (friction: review). No license declared on the model card. (license file, observed 2026-10-24)
- Created 2026-09-23, last modified 2026-09-23. (HF API, observed 2026-10-24)
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | Qwen3_5ForConditionalGeneration |
| Model type | qwen3_5 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 4,659,861,248 · F32: 3,840 |
| Size band | M |
| MoE | no |
| Context length | 262,144 (config.json max_position_embeddings) |
| License | Not declared |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · Qwen3_5ForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen3_5ForConditionalGeneration · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Hardware fit
3 estimates
Hardware fit ESTIMATE
Weights-only memory for Tev1-4B-experimental: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 11 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 5.6 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 2.8 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Decision facts
catalog
Decision-model catalog curated
| How it was made | full fine-tune (whole weights published) |
|---|---|
| Lineage bucket | F - fine-tune of an open model (public/synthetic data) |
| Lineage evidence | board file inspection (adapter/head/weight files) + HF base_model field |
| Base model | Qwen/Qwen3.5-4B-Base |
| DI 0.2.1 score | 29.24 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.1040 |
| Median latency | 35.8 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | 0.042 (Together)/M |
| Source | https://huggingface.co/togethercomputer/Tev1-4B-experimental |
All variants
8 variants
Lineage
Base model: Qwen/Qwen3.5-4B
quantized: 6finetune: 2
Top variants (8 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| bartowski/togethercomputer_Tev1-4B-experimental-GGUF | quantized | GGUF | — | — | — | bartowski | 5 | 6.7k |
| prithivMLmods/Tev1-4B-experimental-GGUF | quantized | GGUF | — | — | apache-2.0 | prithivMLmods | 3 | 1.5k |
| SirSahOl/Tev1-4B-experimental-chat-mlx-16bit | finetune | mlx | 4.21B | M | unknown | SirSahOl | 0 | 402 |
| gavinmroy/Tev1-4B-experimental-mlx | finetune | mlx | 4.21B | M | — | gavinmroy | 0 | 273 |
| gavinmroy/Tev1-4B-experimental-mlx-4bit | quantized | mlx | 4.21B | M | — | gavinmroy | 0 | 98 |
| SirSahOl/Tev1-4B-experimental-chat-mlx-4bit | quantized | mlx | 4.21B | M | unknown | SirSahOl | 0 | 93 |
| SirSahOl/Tev1-4B-experimental-chat-mlx-8bit | quantized | mlx | 4.21B | M | unknown | SirSahOl | 0 | 72 |
| goldenfox/tev1-4b-decision-onnx | quantized | — | — | — | other | goldenfox | 1 | 0 |
Repository changelog
5 commits
Repository changelog 5 commits
All providers
1 provider · 1 endpoint
Where to run 1 providers · 1 endpoints
Hosted endpoints observed for Tev1-4B-experimental, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.04/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Together AI hf | together/Tev1-4B-experimental | 32K | — | $0.04 | $0.00 | 33.1 | 185 ms | yes | live | 2026-10-25 |
Similar models
3 models
Similar models
- Qwen3-4B · 4.02B same size band (M), same task (text-generation), permissive license
- Qwen3-4B-Instruct-2507 · 4.02B same size band (M), same task (text-generation), permissive license
- Qwen3-4B-Thinking-2507 · 4.02B same size band (M), same task (text-generation), more providers, permissive license
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:43 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:17 UTC · Last verified 2026-10-25
Follow Tev1-4B-experimental
Watch this model
- /feeds/models/togethercomputer--Tev1-4B-experimental.xml(RSS 2.0) · every change to Tev1-4B-experimental
- /feeds/families/togethercomputer--Tev1-experimental.xml(RSS 2.0) · every change across the Tev1-experimental family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.