Instructions to use Jetlink/JetLLMLite-v1.1-36B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jetlink/JetLLMLite-v1.1-36B-A3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Jetlink/JetLLMLite-v1.1-36B-A3B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Jetlink/JetLLMLite-v1.1-36B-A3B") model = AutoModelForMultimodalLM.from_pretrained("Jetlink/JetLLMLite-v1.1-36B-A3B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jetlink/JetLLMLite-v1.1-36B-A3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jetlink/JetLLMLite-v1.1-36B-A3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jetlink/JetLLMLite-v1.1-36B-A3B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Jetlink/JetLLMLite-v1.1-36B-A3B
- SGLang
How to use Jetlink/JetLLMLite-v1.1-36B-A3B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Jetlink/JetLLMLite-v1.1-36B-A3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jetlink/JetLLMLite-v1.1-36B-A3B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Jetlink/JetLLMLite-v1.1-36B-A3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jetlink/JetLLMLite-v1.1-36B-A3B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use Jetlink/JetLLMLite-v1.1-36B-A3B with Docker Model Runner:
docker model run hf.co/Jetlink/JetLLMLite-v1.1-36B-A3B
- JetLLMLite-3.6
- JetLLMLite-3.6 (Tรผrkรงe)
- Model รzeti
- Temel รzellikler
- Kullanฤฑm Amacฤฑ
- Model Detaylarฤฑ
- Performans Konumlandฤฑrmasฤฑ
- Donanฤฑm Gereksinimleri
- Yazฤฑlฤฑm Gereksinimleri
- Hฤฑzlฤฑ Baลlangฤฑรง
- Serving รrnekleri
- Uzun Baฤlam Notlarฤฑ
- Gรผรงlรผ Yรถnler
- Sฤฑnฤฑrlamalar
- Kapsam Dฤฑลฤฑ / Dikkat Gerektiren Kullanฤฑmlar
- Lisans
- Atฤฑf
- Atฤฑf / Citation
- Feragatname
- Model รzeti
JetLLMLite-3.6
This repository hosts an organization-managed copy of JetLLMLite-3.6 for advanced coding, reasoning, long-context, and agentic AI workloads.
It is intended for teams that want to manage deployment, access, and internal distribution from their own namespace while preserving compatibility with the upstream model ecosystem.
Model Summary
JetLLMLite-3.6 is an open-weight post-trained model released in Hugging Face Transformers format. According to the official model card, these artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, and KTransformers. The model is described as a Causal Language Model with Vision Encoder, with 35B total parameters and 3B activated parameters, plus 262,144 native context length extensible up to 1,010,000 tokens. :contentReference[oaicite:0]{index=0}
Key Features
- 35B total parameters
- 3B activated parameters
- MoE-based architecture
- Vision-language capability
- Strong coding and agentic performance
- 262,144 native context length
- Extensible context up to 1,010,000 tokens
- Compatible with Transformers, vLLM, SGLang, and KTransformers :contentReference[oaicite:1]{index=1}
Intended Use
This model is suitable for:
- advanced chat assistants
- coding assistants
- repository-level reasoning
- agentic workflows
- multimodal question answering
- long-context document understanding
- RAG and tool-using systems
- enterprise AI applications
- research and benchmarking :contentReference[oaicite:2]{index=2}
Model Details
Architecture
According to the official Qwen model card:
- Model type: Causal Language Model with Vision Encoder
- Training stage: Pre-training & Post-training
- Total parameters: 35B
- Activated parameters: 3B
- Hidden dimension: 2048
- Token embedding: 248320 (padded)
- Number of layers: 40
- Hidden layout: 10 ร (3 ร (Gated DeltaNet โ MoE) โ 1 ร (Gated Attention โ MoE))
- Number of experts: 256
- Activated experts: 8 Routed + 1 Shared
- Expert intermediate dimension: 512
- MTP: trained with multi-steps
- Context length: 262,144 natively and extensible up to 1,010,000 tokens :contentReference[oaicite:3]{index=3}
Performance Positioning
The official model card highlights JetLLMLite-3.6 as an open-weight model built with a focus on stability and real-world utility, with notable emphasis on:
- Agentic coding
- Frontend workflows
- Repository-level reasoning
- Thinking preservation across historical context :contentReference[oaicite:4]{index=4}
Hardware Requirements
This model does not have a single universal minimum hardware requirement for every deployment scenario.
Actual requirements depend on:
- inference backend
- precision / quantization
- batch size
- context length
- whether vision inputs are enabled
- concurrency
- latency targets
- KV cache configuration :contentReference[oaicite:5]{index=5}
Minimum System Requirements
Because the model has 35B total parameters and 3B activated parameters, real VRAM usage can vary substantially depending on the runtime and workload profile. The upstream model card does not publish a single hard minimum VRAM number. However, for practical planning, the following guidance is reasonable:
- Estimated practical minimum for heavily quantized local inference: around 24 GB VRAM
- More realistic for smoother local / development usage: 48โ80 GB VRAM
- Recommended for production serving of the original model: multi-GPU or high-memory datacenter GPU environments
- Recommended for long-context or multimodal serving: high-memory datacenter-class infrastructure :contentReference[oaicite:6]{index=6}
Note: these values are practical estimates for deployment planning, not universal hard limits. Real memory usage can increase significantly with longer contexts, multimodal inputs, larger batch sizes, and serving-framework overhead.
Reference Hardware
The upstream model card provides official serving examples for this model with common inference stacks such as vLLM, SGLang, and Transformers, and includes a Docker example for SGLang. For practical deployment planning:
- Quantized local experimentation: high-memory single-GPU environments may be sufficient
- Standard production-oriented serving: modern datacenter GPUs are recommended
- Long-context and higher-concurrency serving: multi-GPU deployment is the safer reference setup
- Multimodal production workloads: high-memory server infrastructure is strongly recommended :contentReference[oaicite:7]{index=7}
Practical Recommendation
For most teams:
- start with quantized evaluation if you are testing locally
- benchmark using your real context lengths
- use dedicated serving stacks such as vLLM or SGLang
- reserve high-memory infrastructure for production-scale or long-context workloads :contentReference[oaicite:8]{index=8}
Software Requirements
Recommended environment:
- Python 3.10+
- Linux
- CUDA-enabled GPU environment
- One of the following runtimes:
- Transformers
- vLLM
- SGLang
- KTransformers
The official model card also notes that the latest transformers is required for JetLLMLite-3.6 and recommends ensuring torchvision and pillow are installed for multimodal use. :contentReference[oaicite:9]{index=9}
Common dependencies may include:
torchtransformerstorchvisionpillow
Quickstart
Install Transformers:
pip install "transformers[serving]"
Basic loading example:
from transformers import pipeline
pipe = pipeline(
"image-text-to-text",
model="Jetlink/JetLLMLite-3.6",
trust_remote_code=True
)
Serving Examples
vLLM
vllm serve Jetlink/JetLLMLite-3.6
SGLang
docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "Jetlink/JetLLMLite-3.6" \
--host 0.0.0.0 \
--port 30000
Docker Model Runner
docker model run hf.co/Jetlink/JetLLMLite-3.6
Long Context Notes
JetLLMLite-3.6 natively supports 262,144 tokens and can be extended up to 1,010,000 tokens. The official model card includes YaRN-style rope scaling configuration guidance for long-context usage. :contentReference[oaicite:10]{index=10}
Strengths
- strong coding and agentic capabilities
- improved frontend and repository-level reasoning
- multimodal support
- very long native context
- extensible ultra-long context support
- modern MoE architecture
- compatibility with popular open inference frameworks :contentReference[oaicite:11]{index=11}
Limitations
- infrastructure requirements can be substantial depending on deployment style
- long-context inference can greatly increase memory pressure
- multimodal workloads add additional overhead
- local deployment practicality depends heavily on quantization and runtime choices
- real-world latency and throughput vary significantly by framework and hardware configuration
Out-of-Scope / Cautionary Use
Outputs should be reviewed before use in:
- medical decision-making
- legal advice
- safety-critical automation
- high-stakes financial decisions
- fully autonomous actions without validation
- sensitive production workflows without guardrails
Human review, tool validation, and policy controls are strongly recommended.
License
This repository follows the same license as the upstream release.
- License: Apache-2.0
If you redistribute, fine-tune, quantize, or otherwise modify this model, make sure your usage remains compliant with the upstream license and attribution requirements. :contentReference[oaicite:12]{index=12}
Attribution
Original upstream model:
Qwen/Qwen3.6-35B-A3B
This repository is an organization-managed copy and is not the original upstream source.
Citation
Please cite the original JetLLMLite-3.6 release when using this model in research, evaluation, or production documentation.
Disclaimer
This repository may include packaging, naming, or deployment-oriented changes for organizational use.
For official updates, benchmark details, long-context settings, and upstream release notes, refer to the original Qwen model card. :contentReference[oaicite:13]{index=13}
JetLLMLite-3.6 (Tรผrkรงe)
Bu depo, geliลmiล kodlama, akฤฑl yรผrรผtme, uzun baฤlam ve agentic AI iล yรผkleri iรงin JetLLMLite-3.6 modelinin kurum tarafฤฑndan yรถnetilen bir kopyasฤฑnฤฑ barฤฑndฤฑrฤฑr.
Bu depo; modeli kendi namespaceโi altฤฑnda yรถnetmek, eriลimi kontrol etmek ve daฤฤฑtฤฑmฤฑ kolaylaลtฤฑrmak isteyen ekipler iรงin hazฤฑrlanmฤฑลtฤฑr. Amaรง, upstream model ekosistemiyle uyumluluฤu koruyarak kurumsal kullanฤฑm saฤlamaktฤฑr.
Model รzeti
JetLLMLite-3.6 resmi model kartฤฑna gรถre bu artefaktlar Hugging Face Transformers, vLLM, SGLang ve KTransformers ile uyumludur. Model, Vision Encoder iรงeren bir Causal Language Model olarak tanฤฑmlanฤฑr; 35B toplam parametre, 3B aktif parametre, 262.144 token yerel baฤlam ve 1.010.000 tokenโa kadar geniลletilebilir baฤlam sunar. :contentReference[oaicite:14]{index=14}
Temel รzellikler
- 35B toplam parametre
- 3B aktif parametre
- MoE tabanlฤฑ mimari
- Vision-language kabiliyeti
- Gรผรงlรผ kodlama ve agentic performans
- 262.144 token yerel baฤlam
- 1.010.000 tokenโa kadar geniลletilebilir baฤlam
- Transformers, vLLM, SGLang ve KTransformers ile uyumluluk :contentReference[oaicite:15]{index=15}
Kullanฤฑm Amacฤฑ
Bu model aลaฤฤฑdaki senaryolar iรงin uygundur:
- geliลmiล sohbet asistanlarฤฑ
- kodlama asistanlarฤฑ
- repository seviyesinde akฤฑl yรผrรผtme
- agentic workflow yapฤฑlarฤฑ
- multimodal soru-cevap
- uzun baฤlamlฤฑ dokรผman anlama
- RAG ve tool-using sistemler
- kurumsal AI uygulamalarฤฑ
- araลtฤฑrma ve benchmark รงalฤฑลmalarฤฑ :contentReference[oaicite:16]{index=16}
Model Detaylarฤฑ
Mimari
Resmi Qwen model kartฤฑna gรถre:
- Model tipi: Vision Encoder iรงeren Causal Language Model
- Eฤitim aลamasฤฑ: Pre-training & Post-training
- Toplam parametre: 35B
- Aktif parametre: 3B
- Hidden dimension: 2048
- Token embedding: 248320 (padded)
- Katman sayฤฑsฤฑ: 40
- Hidden layout: 10 ร (3 ร (Gated DeltaNet โ MoE) โ 1 ร (Gated Attention โ MoE))
- Expert sayฤฑsฤฑ: 256
- Aktif expert: 8 Routed + 1 Shared
- Expert intermediate dimension: 512
- MTP: multi-steps ile eฤitilmiล
- Baฤlam uzunluฤu: yerel olarak 262.144, geniลletilmiล olarak 1.010.000 tokenโa kadar :contentReference[oaicite:17]{index=17}
Performans Konumlandฤฑrmasฤฑ
Resmi model kartฤฑ JetLLMLite-3.6โyฤฑ รถzellikle ลu alanlarda รถne รงฤฑkarฤฑr:
- Agentic coding
- Frontend workflowโleri
- Repository-level reasoning
- Geรงmiล mesajlardan dรผลรผnme baฤlamฤฑnฤฑ koruma :contentReference[oaicite:18]{index=18}
Donanฤฑm Gereksinimleri
Bu model iรงin her senaryoya uyan tek bir evrensel minimum donanฤฑm gereksinimi yoktur.
Gerรงek ihtiyaรงlar ลunlara baฤlฤฑdฤฑr:
- inference backend
- precision / quantization
- batch size
- baฤlam uzunluฤu
- vision girdilerinin aรงฤฑk olup olmamasฤฑ
- concurrency
- latency hedefleri
- KV cache yapฤฑlandฤฑrmasฤฑ :contentReference[oaicite:19]{index=19}
Minimum Sistem Gereksinimleri
Model 35B toplam parametreye ve 3B aktif parametreye sahip olduฤu iรงin gerรงek VRAM kullanฤฑmฤฑ runtime ve iล yรผkรผne gรถre ciddi biรงimde deฤiลebilir. Upstream model kartฤฑ tek bir kesin minimum VRAM sayฤฑsฤฑ vermez. Ancak pratik planlama iรงin ลu rehber uygundur:
- Aฤฤฑr quantized local inference iรงin tahmini pratik minimum: yaklaลฤฑk 24 GB VRAM
- Daha rahat local / geliลtirme kullanฤฑmฤฑ iรงin daha gerรงekรงi seviye: 48โ80 GB VRAM
- Orijinal modelin production servingโi iรงin รถnerilen: รงoklu GPU veya yรผksek bellekli datacenter GPU ortamlarฤฑ
- Uzun baฤlam veya multimodal serving iรงin รถnerilen: yรผksek bellekli datacenter sฤฑnฤฑfฤฑ altyapฤฑ :contentReference[oaicite:20]{index=20}
Not: bunlar deployment planlamasฤฑ iรงin pratik tahminlerdir; evrensel kesin sฤฑnฤฑrlar deฤildir. Daha uzun baฤlamlar, multimodal girdiler, bรผyรผk batch size ve serving framework kaynaklฤฑ ek yรผkler gerรงek bellek kullanฤฑmฤฑnฤฑ ciddi ลekilde artฤฑrabilir.
Referans Donanฤฑm
Upstream model kartฤฑ bu model iรงin vLLM, SGLang ve Transformers gibi inference stackโleriyle resmi serving รถrnekleri sunar ve ayrฤฑca SGLang iรงin bir Docker รถrneฤi iรงerir. Pratik daฤฤฑtฤฑm planlamasฤฑ iรงin:
- Quantized local denemeler: yรผksek bellekli tek GPU ortamlarฤฑ yeterli olabilir
- Standart production serving: modern datacenter GPUโlar รถnerilir
- Uzun baฤlam ve daha yรผksek concurrency: รงoklu GPU daฤฤฑtฤฑmฤฑ daha gรผvenli referanstฤฑr
- Multimodal production iล yรผkleri: yรผksek bellekli sunucu altyapฤฑsฤฑ gรผรงlรผ ลekilde รถnerilir :contentReference[oaicite:21]{index=21}
Pratik รneri
รoฤu ekip iรงin en mantฤฑklฤฑ yaklaลฤฑm:
- local testte quantized deฤerlendirme ile baลlamak
- gerรงek baฤlam uzunluklarฤฑyla benchmark almak
- vLLM veya SGLang gibi รถzel serving stackโleri kullanmak
- production รถlรงeฤi veya uzun baฤlam iรงin yรผksek bellekli altyapฤฑ ayฤฑrmak :contentReference[oaicite:22]{index=22}
Yazฤฑlฤฑm Gereksinimleri
รnerilen ortam:
- Python 3.10+
- Linux
- CUDA destekli GPU ortamฤฑ
- ลu runtimeโlardan biri:
- Transformers
- vLLM
- SGLang
- KTransformers
Resmi model kartฤฑ ayrฤฑca JetLLMLite-3.6 iรงin en gรผncel transformers sรผrรผmรผnรผn gerektiฤini ve multimodal kullanฤฑm iรงin torchvision ile pillow kurulu olmasฤฑ gerektiฤini belirtir. :contentReference[oaicite:23]{index=23}
Yaygฤฑn baฤฤฑmlฤฑlฤฑklar:
torchtransformerstorchvisionpillow
Hฤฑzlฤฑ Baลlangฤฑรง
Transformers kurulumu:
pip install "transformers[serving]"
Temel yรผkleme รถrneฤi:
from transformers import pipeline
pipe = pipeline(
"image-text-to-text",
model="Jetlink/JetLLMLite-3.6",
trust_remote_code=True
)
Serving รrnekleri
vLLM
vllm serve Jetlink/JetLLMLite-3.6
SGLang
docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "Jetlink/JetLLMLite-3.6" \
--host 0.0.0.0 \
--port 30000
Docker Model Runner
docker model run hf.co/Jetlink/JetLLMLite-3.6
Uzun Baฤlam Notlarฤฑ
JetLLMLite-3.6 yerel olarak 262.144 token destekler ve 1.010.000 tokenโa kadar geniลletilebilir. Resmi model kartฤฑ uzun baฤlam kullanฤฑmฤฑ iรงin YaRN tabanlฤฑ rope scaling yapฤฑlandฤฑrma rehberi de iรงerir. :contentReference[oaicite:24]{index=24}
Gรผรงlรผ Yรถnler
- gรผรงlรผ kodlama ve agentic kabiliyetler
- geliลmiล frontend ve repository-level reasoning
- multimodal destek
- รงok uzun yerel baฤlam
- geniลletilebilir ultra uzun baฤlam
- modern MoE mimarisi
- popรผler aรงฤฑk inference frameworkโleriyle uyumluluk :contentReference[oaicite:25]{index=25}
Sฤฑnฤฑrlamalar
- deployment tipine gรถre altyapฤฑ ihtiyacฤฑ ciddi olabilir
- uzun baฤlam inference bellek baskฤฑsฤฑnฤฑ bรผyรผk รถlรงรผde artฤฑrabilir
- multimodal iล yรผkleri ek kaynak tรผketir
- local kullanฤฑmฤฑn pratikliฤi quantization ve runtime seรงimine รงok baฤlฤฑdฤฑr
- gerรงek dรผnya latency ve throughput deฤerleri framework ve donanฤฑm yapฤฑlandฤฑrmasฤฑna gรถre ciddi biรงimde deฤiลir
Kapsam Dฤฑลฤฑ / Dikkat Gerektiren Kullanฤฑmlar
รฤฑktฤฑlar ลu alanlarda insan kontrolรผ olmadan kullanฤฑlmamalฤฑdฤฑr:
- tฤฑbbi karar verme
- hukuki tavsiye
- gรผvenlik kritik otomasyon
- yรผksek riskli finansal kararlar
- doฤrulama olmadan tam otonom aksiyonlar
- korumasฤฑz hassas production iล akฤฑลlarฤฑ
ฤฐnsan incelemesi, tool doฤrulamasฤฑ ve politika kontrolleri gรผรงlรผ ลekilde รถnerilir.
Lisans
Bu depo, upstream sรผrรผmle aynฤฑ lisansฤฑ takip eder.
- Lisans: Apache-2.0
Modeli yeniden daฤฤฑtฤฑyor, fine-tune ediyor, quantize ediyor veya baลka ลekilde deฤiลtiriyorsan; kullanฤฑmฤฑnฤฑn upstream lisans ve attribution gereklilikleriyle uyumlu olduฤundan emin olmalฤฑsฤฑn. :contentReference[oaicite:26]{index=26}
Atฤฑf
Orijinal upstream model:
Qwen/Qwen3.6-35B-A3B
Bu depo, kurum tarafฤฑndan yรถnetilen bir kopyadฤฑr ve orijinal upstream kaynak deฤildir.
Atฤฑf / Citation
Bu modeli araลtฤฑrma, deฤerlendirme veya production dokรผmantasyonunda kullanฤฑyorsan, lรผtfen orijinal Qwen3.6 sรผrรผmรผne atฤฑf yap.
Feragatname
Bu depo, kurumsal kullanฤฑm amacฤฑyla paketleme, isimlendirme veya daฤฤฑtฤฑm odaklฤฑ bazฤฑ deฤiลiklikler iรงerebilir.
Resmi gรผncellemeler, benchmark detaylarฤฑ, uzun baฤlam ayarlarฤฑ ve upstream sรผrรผm notlarฤฑ iรงin orijinal Qwen model kartฤฑna bakฤฑlmalฤฑdฤฑr. :contentReference[oaicite:27]{index=27}
- Downloads last month
- 14