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 (2023-10-05), grey ticks are repo commits.
llava-v1.5-7b
liuhaotian Not declared out 3 years ago
Images and text in, text out, 4K tokens of context.
Verified 2026-10-25 Rank #542 in LLMs · score 75.2 method v1 Sources 3 Downloads 30d 83.2k · #332 of 619 tracked
Do people use it?83.2kdownloads, 30 days#332 of 619 we track · below the median+1 likes, downloads −4% this week566 likesHugging Face2026-10-24
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.
No API provider serves it, so its downloads are people running it themselves: 4 quantized builds and 61 Spaces.
- As a service0no API provider listed
- On own hardware4quantized builds
- Built on13142 fine-tunes · 89 adapters · 0 merges
- In apps61Hugging Face Spaces
Top Spaces running it: JackAILab/ConsistentID ♥ 60 · Senqiao/VisionZip ♥ 12 · JackAILab/ConsistentID-SDXL ♥ 11 · luis112/text-generation-webui ♥ 9
What people built on it
135 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
135 derivatives on the Hub, most of them adapters
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
3 cited sentences
Summary generated, cited
LLaVA-v1.5-7B is an auto-regressive language model based on the transformer architecture for image-text-to-text tasks.[1][2] The model is used for research on large multimodal models and chatbots.[3] It was trained in September 2023 using a mixture of 558K filtered image-text pairs and 158K GPT-generated multimodal instruction-following data.[4][5][6]
- model type
- “auto-regressive language model, based on the transformer …”
- “research on large multimodal models and chatbots”
- “trained in September 2023”
- “558K filtered image-text pairs”
- “158K GPT-generated multimodal instruction-following data”
Generated 2026-10-07 15:13 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Use-case evidence
3 use cases
What it is good at 3 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.
Facts
17 fields
Listed in LLMs
Facts
- Context length is 4,096 tokens (4K). (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 2023-10-05, last modified 2024-05-08. (HF API, observed 2026-10-24)
| Pipeline tag | image-text-to-text |
|---|---|
| Library | transformers |
| Architectures | LlavaLlamaForCausalLM |
| Model type | llava |
| Dtype | float16 |
| MoE | no |
| Context length | 4,096 (config.json max_position_embeddings) |
| License | Not declared |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · LlavaLlamaForCausalLM · 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.
All variants
40 variants
Lineage
quantized: 4finetune: 42adapter: 89
Top variants (40 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| second-state/Llava-v1.5-7B-GGUF | quantized | GGUF | — | — | llama2 | second-state | 20 | 243.4k |
| X-iZhang/Med-CXRGen-F | finetune | — | 6.76B | M | apache-2.0 | X-iZhang | 2 | 84.1k |
| X-iZhang/Med-CXRGen-I | finetune | — | 6.76B | M | apache-2.0 | X-iZhang | 2 | 62.2k |
| ChaimZhu/LLaVA-3D-7B | finetune | — | 7.08B | M | apache-2.0 | ChaimZhu | 6 | 54.3k |
| Senqiao/LISA_Plus_7b | finetune | — | — | — | apache-2.0 | Senqiao | 9 | 18.9k |
| zhuoyanxu/ada-llava-L-v1.5-7b | finetune | — | 6.78B | M | llama2 | zhuoyanxu | 0 | 8k |
| FreedomIntelligence/llava-v1.5-7b-TRIM | finetune | — | 7.19B | M | apache-2.0 | FreedomIntelligence | 1 | 1.1k |
| kesenZhaoNTU/UV-CoT | finetune | — | 6.76B | M | cc-by-nc-nd-4.0 | kesenZhaoNTU | 5 | 749 |
| salma-remyx/spacellava-1.5-7b | finetune | — | 7.06B | M | apache-2.0 | salma-remyx | 1 | 810 |
| Kun-Xiang/AtomThink-LLaVA1.5-7B | finetune | — | 7.06B | M | — | Kun-Xiang | 3 | 698 |
| psp-dada/LLaVA-v1.5-7B-SENTINEL | adapter | — | — | — | apache-2.0 | psp-dada | 1 | 442 |
| OPEA/llava-v1.5-7b-int4-sym-inc | quantized | int4 | 1.45B | S | — | OPEA | 1 | 429 |
| wayneicloud/VPP-LLaVA-7b | finetune | — | 7.13B | M | apache-2.0 | wayneicloud | 0 | 430 |
| jeffrey423/ToothXpert | adapter | — | — | — | apache-2.0 | jeffrey423 | 0 | 429 |
| shuoxing/llava-v1.5-7b-Math-R1-Reason | finetune | — | 7.06B | M | apache-2.0 | shuoxing | 0 | 308 |
| Polly1231/llava-v1.5-7b-vlguard-without_helpfulnessData-temp-seed-42-changed_groundtruth_format | adapter | — | — | — | — | Polly1231 | 0 | 254 |
| erenzhou/GeoGround | finetune | — | — | — | — | erenzhou | 4 | 0 |
| nahidalam/llava-aimv2 | finetune | — | 327K | S | apache-2.0 | nahidalam | 0 | 192 |
| ForeverBlue/LLaVA-1.5-7B-GRACE-W4G128 | quantized | — | 7.06B | M | apache-2.0 | ForeverBlue | 1 | 137 |
| Polly1231/llava-v1.5-7b-lora-VLGuard-withoutHelpnessData | adapter | — | — | — | — | Polly1231 | 0 | 179 |
| starreeze/llava-efuf-7b | finetune | — | — | — | gpl-3.0 | starreeze | 3 | 0 |
| ForeverBlue/LLaVA-1.5-7B-GRACE-W4G128-AWQ | quantized | AWQ | 1.45B | S | apache-2.0 | ForeverBlue | 1 | 82 |
| henry984/Mobius | finetune | — | — | — | apache-2.0 | henry984 | 0 | 129 |
| Zongxiong/llava-v1.5-7b-vlguard-lora | adapter | — | — | — | — | Zongxiong | 0 | 117 |
| Shion1124/vlm-lora-agentic-rag | adapter | — | — | — | apache-2.0 | Shion1124 | 0 | 102 |
| mbhosale/FairLLaVA | adapter | — | — | — | apache-2.0 | mbhosale | 2 | 0 |
| uncertainty-in-planning/llava-v1.5-7b-baseline-800 | adapter | — | — | — | — | uncertainty-in-planning | 0 | 99 |
| Polly1231/llava-v1.5-7b-lora-direct_rejection | adapter | — | — | — | — | Polly1231 | 0 | 90 |
| ArtInSight/ngak1-GPT-001 | finetune | — | 7.06B | M | mit | ArtInSight | 0 | 90 |
| ernestoBocini/finetuning_capitoning_itclass | adapter | — | — | — | — | ernestoBocini | 0 | 89 |
| Huanghz/align2llava-7b-lora-question | finetune | — | — | — | llama2 | Huanghz | 0 | 88 |
| Polly1231/llava-v1.5-7b-vlguard-without_helpfulnessData-2025-2-27-16.12 | adapter | — | — | — | — | Polly1231 | 0 | 87 |
| whyisverysmart/Fourier-LLaVA-v1.5-7B-256 | finetune | — | 7.06B | M | apache-2.0 | whyisverysmart | 0 | 82 |
| tennant/agent-7b-lora-3ep-llava-1.5-7b | adapter | — | — | — | — | tennant | 0 | 81 |
| Polly1231/llava-v1.5-7b-lora-change_order_reasoning | adapter | — | — | — | — | Polly1231 | 0 | 80 |
| iLearn-Lab/NeurIPS25-SymMPO-7B | finetune | — | 7.06B | M | apache-2.0 | iLearn-Lab | 0 | 80 |
| Huanghz/align2llava-7b-lora-answer | finetune | — | — | — | llama2 | Huanghz | 0 | 78 |
| liyun0607/CausalSceneNarration-LoRA | adapter | — | — | — | llama2 | liyun0607 | 1 | 26 |
| stash/llava-v1.5-13b-task-lora-TEST-20240802_235424 | adapter | — | — | — | — | stash | 0 | 72 |
| stash/llava-v1.5-13b-task-lora-20240803_000053 | adapter | — | — | — | — | stash | 1 | 22 |
Repository changelog
5 commits
Similar models
3 models
Similar models
- Winnow-12B same task (image-text-to-text), permissive license
- Winnow-E4B same task (image-text-to-text), permissive license
- opt-125m closest by size and task
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:41 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:13 UTC · Last verified 2026-10-25
Follow llava-v1.5-7b
Watch this model
- /feeds/models/liuhaotian--llava-v1.5-7b.xml(RSS 2.0) · every change to llava-v1.5-7b
- /feeds/families/liuhaotian--llava-v1.5.xml(RSS 2.0) · every change across the llava-v1.5 family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.