Stability AI · Stable Code

Stable Code Instruct 3B

Stable Code Instruct 3B is a 3B code-generation and chat model available through supported Badgr execution routes.

Last validated or meaningfully updated: 2026-07-27

ChatCodingEdge-capableFine-tunable

✓ Verified by Badgr

Last verified 2026-09-26

badgr serve stabilityai/stable-code-instruct-3b --max-cost 1
Provider
RunPod
GPU
NVIDIA H100 PCIe
Time to verified
346.8s
Deployment
dep-48409af0ae
  • ✓ vLLM started
  • ✓ inference verification passed
  • ✓ final_state = VERIFIED
  • ✓ teardown completed

Real cross-provider fallback: 4 other GPU offers had no capacity at request time before this run landed on the NVIDIA H100 PCIe above and verified.

Raw evidence
verify_command model=stabilityai/stable-code-instruct-3b ok=True
final_state=VERIFIED failure_class=None provider=runpod providers_tried=5 spend_usd=0.0000 elapsed=346.8s

Run from Badgr's local development environment. Documents that this deployment path works end-to-end for this model.

Availability

✓ Badgr AI API

Available through Badgr

✓ Dedicated endpoint

Available through Badgr

✓ Custom GPU deployment

Available through Badgr

Deployment profile

Architecture
StableLmForCausalLM
Licence
Stability AI Non-Commercial
Minimum VRAM
~10GB
Context
16K tokens

Recommended: RTX 4090 24GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.

Model identity

Languages
en
Updated
2 years ago
HuggingFace revision
20e21f0e81

Popularity and trust

Downloads (last month)

2.2K

Likes

189

Spaces using this model

30

Files and formats

Weight formats

Safetensors, GGUF

Repository files

13

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

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

RuntimeStatusNotes
vLLMEstimatedUsed for Badgr dedicated endpoints
TransformersDeclared by sourceBasic fallback
llama.cppDeclared by sourceGGUF weights available in repo
SGLangUnknownNot evaluated
TensorRT-LLMUnknownConversion may be required
TGIUnknownNot evaluated

Call this model through Badgr

curl https://api.aibadgr.com/v1/chat/completions \
  -H "Authorization: Bearer $BADGR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"stabilityai/stable-code-instruct-3b","messages":[{"role":"user","content":"Hello"}]}'

Ready-to-run Badgr configurations

Quick test

badgr serve stabilityai/stable-code-instruct-3b --max-cost 2

Validated dedicated endpoint command

badgr serve stabilityai/stable-code-instruct-3b --gpu RTX 4090 --max-cost 10

Advanced 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

$0.45 – $0.45/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

Estimated

starting 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

Estimated

starting 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

Estimated

starting 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

Estimated

starting 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

Estimated

starting 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

Estimated

starting 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

Known limitations

  • Memory use increases with context length and concurrency.

Related troubleshooting