Unsloth · Qwen 3.5
Qwen 3.5 4B MTP GGUF
Verified by Badgr · ServeQwen 3.5 4B MTP GGUF is a 4.3B chat and text-generation model available through supported Badgr execution routes.
Last validated or meaningfully updated: 2026-10-08
✓ Verified by Badgr · llama.cpp · Serve
Last verified 2026-10-08
badgr serve --runtime llama.cpp --hf-repo unsloth/Qwen3.5-4B-MTP-GGUF --hf-file Qwen3.5-4B-UD-Q4_K_XL.gguf --gpu RTX_4090 --max-cost 1.5- GPU
- NVIDIA GeForce RTX 4090Reported by the provider, not confirmed inside the container
- Time to verified
- 83s
- Deployment
- dep-327a4ec672
- ✓ llama-server started
- ✓ /health returned HTTP 200
- ✓ Chat completion returned the expected reply
- ✓ final_state = VERIFIED
- ✓ Teardown completed
Reasoning model: the reply arrived with max_tokens=400 but was empty at max_tokens=16, because the first tokens are reasoning. Use a larger max_tokens.
GitHub issue this run was for: unslothai/unsloth#12695
Raw evidence
final_state=VERIFIED failure_class=None providers_tried=1 spend_usd=0.0040 elapsed=83.0s
Run from Badgr's local development environment. Documents that this deployment path works end-to-end for this model.
Availability
Not yet Badgr AI API
Not currently validated
✓ Dedicated endpoint
Available through Badgr
✓ Custom GPU deployment
Available through Badgr
Deployment profile
- Architecture
- qwen35 (GGUF)
- Licence
- Apache-2.0
- Minimum VRAM
- ~13GB
- Context
- 256K tokens
Recommended: RTX 4090 24GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.
Model identity
- Base model
- Qwen/Qwen3.5-4B
- Updated
- 4 months ago
- HuggingFace revision
- 86835bf994
Popularity and trust
Downloads (last month)
101.8K
Likes
101
Spaces using this model
4
Files and formats
Weight formats
GGUF
Repository files
27
Chat template
Not detected
GPU deployment scenarios
Estimated from parameter count and quantisation. Will switch to “Verified by Badgr” once a real run backs a tier.
Testing
RTX 4090 24GB
Short context, low concurrency
Small production
L40S 48GB
8K context, 1-4 concurrent requests
Higher throughput
A100 80GB
32K context, continuous batching
Large production
RTX 4090 24GB
Higher concurrency
Estimated — multimodal inputs, long context, and concurrency all increase real VRAM use beyond this estimate.
Also runs well on L40S 48GB, A100 40GB. Available in United States, Europe.
Serving compatibility
| Runtime | Status | Notes |
|---|---|---|
| vLLM | Estimated | Used for Badgr dedicated endpoints |
| Transformers | Declared by source | Basic fallback |
| llama.cpp | Verified by Badgr | Confirmed by a real badgr serve run (deployment dep-327a4ec672) |
| SGLang | Unknown | Not evaluated |
| Ollama | Unknown | Not evaluated |
| Diffusers | Unknown | Not evaluated |
| PyTorch | Unknown | Not evaluated |
| TensorRT-LLM | Unknown | Conversion may be required |
| TGI | Unknown | Not evaluated |
Ready-to-run Badgr configurations
Quick test
badgr serve unsloth/Qwen3.5-4B-MTP-GGUF --max-cost 2Validated dedicated endpoint command
badgr serve unsloth/Qwen3.5-4B-MTP-GGUF --gpu RTX 4090 --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
2–5 min
Provider estimate: endpoint cost
$0.18 – $0.50/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
RTX 4090 24GB · United States
Availablefrom $0.18/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · United States
Availablefrom $0.44/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
RTX 4090 24GB · United States
Availablefrom $0.50/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
Known limitations
- Memory use increases with context length and concurrency.