Qwen · Qwen2.5
Qwen2.5-14B-Instruct-GPTQ-Int4
Unverified · community-discovered, not yet reviewedQwen2.5-14B-Instruct-GPTQ-Int4 is a discovered model from public model catalogues. Badgr builds a GPU serving profile from source metadata, estimated VRAM, context length, and available execution routes.
Last validated or meaningfully updated: Dynamic source discovery
Availability
Not yet Badgr AI API
Not currently validated
✓ Dedicated endpoint
Available through Badgr
✓ Custom GPU deployment
Available through Badgr
Deployment profile
- Architecture
- Source metadata pending
- Licence
- Check model card
- Minimum VRAM
- ~32GB
- Context
- Source dependent
Recommended: L40S 48GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.
Model identity
- Base model
- Qwen/Qwen2.5-14B-Instruct
- Languages
- en
- Updated
- 1 years ago
- HuggingFace revision
- 08fdbde5ee
Popularity and trust
Downloads (last month)
60.1K
Likes
27
Spaces using this model
0
Files and formats
Weight formats
Safetensors
Repository files
13
Tokenizer
BPE
Chat template
Available
GPU deployment scenarios
Estimated from parameter count and quantisation. Will switch to “Verified by Badgr” once a real run backs a tier.
Testing
L40S 48GB
Short context, low concurrency
Small production
A100 80GB
8K context, 1-4 concurrent requests
Higher throughput
H100 80GB
32K context, continuous batching
Large production
L40S 48GB
Higher concurrency
Estimated — multimodal inputs, long context, and concurrency all increase real VRAM use beyond this estimate.
Also runs well on A100 80GB, H100 80GB. Available in United States, Europe, Asia Pacific.
Serving compatibility
| Runtime | Status | Notes |
|---|---|---|
| vLLM | Estimated | Used for Badgr dedicated endpoints |
| Transformers | Declared by source | Basic fallback |
| llama.cpp | Requires GGUF conversion | No GGUF weights found in repo |
| SGLang | Unknown | Not evaluated |
| TensorRT-LLM | Unknown | Conversion may be required |
| TGI | Unknown | Not evaluated |
Ready-to-run Badgr configurations
Quick test
badgr serve Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4 --max-cost 2Dedicated endpoint command
badgr serve Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4 --gpu L40S --max-cost 10Advanced configuration (defaults to automatic)
- Runtime
- Quantisation
- GPU and GPU count
- Context length
- Maximum concurrency
- Region
- Maximum hourly spend
- Persistent or capped runtime
Estimated pricing
Provider estimate: cold start
3–6 min
Provider estimate: endpoint cost
$0.86 – $0.99/hr
Idle cost
$0 when stopped
Per-token throughput cost is not shown here: Badgr has not benchmarked this model yet, and this page does not display figures it cannot back with real data.
Recommended Badgr routes
L40S 48GB · United States
Availablefrom $0.86/hr
Best for
ComfyUI, vLLM Endpoint, Qwen 2.5 7B Instruct
Startup: 3–6 min
Reliability: Good
Last checked: just now
L40S 48GB · Europe
Availablefrom $0.86/hr
Best for
ComfyUI, vLLM Endpoint, Qwen 2.5 7B Instruct
Startup: 3–6 min
Reliability: Good
Last checked: just now
L40S 48GB · Asia Pacific
Availablefrom $0.86/hr
Best for
ComfyUI, vLLM Endpoint, Qwen 2.5 7B Instruct
Startup: 3–6 min
Reliability: Good
Last checked: just now
L40S 48GB · United States
Availablefrom $0.99/hr
Best for
ComfyUI, vLLM Endpoint, Qwen 2.5 7B Instruct
Startup: 3–6 min
Reliability: Good
Last checked: just now
L40S 48GB · Europe
Availablefrom $0.99/hr
Best for
ComfyUI, vLLM Endpoint, Qwen 2.5 7B Instruct
Startup: 3–6 min
Reliability: Good
Last checked: just now
L40S 48GB · Asia Pacific
Availablefrom $0.99/hr
Best for
ComfyUI, vLLM Endpoint, Qwen 2.5 7B Instruct
Startup: 3–6 min
Reliability: Good
Last checked: just now
Known limitations
- Source-discovered pages use best-effort metadata until the model is reviewed.
- Licence, gated access, runner compatibility, and exact memory use should be checked before production deployment.