Meta · Llama 3.1

Llama 3.1 70B Instruct GPTQ

Unverified · community-discovered, not yet reviewed

Llama 3.1 70B Instruct is a 70B chat and text-generation model available through supported Badgr execution routes.

Last validated or meaningfully updated: 2026-07-27

ChatLong context

Availability

Not yet Badgr AI API

Not currently validated

Not yet Dedicated endpoint

Not currently validated

Not yet Custom GPU deployment

Not currently validated

Deployment profile

Architecture
LlamaForCausalLM
Licence
Llama 3.1 Community
Minimum VRAM
~53GB
Context
128K tokens

Recommended: A100 80GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.

GPU deployment scenarios

Estimated from parameter count and quantisation. Will switch to “Verified by Badgr” once a real run backs a tier.

Testing

A100 80GB

Short context, low concurrency

Small production

H100 80GB

8K context, 1-4 concurrent requests

Higher throughput

H200 141GB

32K context, continuous batching

Large production

A100 80GB

Higher concurrency

Estimated — multimodal inputs, long context, and concurrency all increase real VRAM use beyond this estimate.

Also runs well on H100 80GB, H200 141GB. Available in United States, Europe, Asia Pacific.

Serving compatibility

RuntimeStatusNotes
vLLMEstimatedUsed for Badgr dedicated endpoints
TransformersUnknownBasic fallback
llama.cppRequires GGUF conversionNo GGUF weights found in repo
SGLangUnknownNot evaluated
TensorRT-LLMUnknownConversion may be required
TGIUnknownNot evaluated

Estimated pricing

Provider estimate: cold start

3–8 min

Provider estimate: endpoint cost

$1.25 – $1.35/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

A100 80GB · United States

Available

from $1.25/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 3–8 min

Reliability: High

Last checked: just now

A100 80GB · Europe

Available

from $1.25/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 3–8 min

Reliability: Good

Last checked: just now

A100 80GB · Asia Pacific

Available

from $1.25/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 3–8 min

Reliability: High

Last checked: just now

A100 80GB · United States

Available

from $1.35/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 3–8 min

Reliability: High

Last checked: just now

A100 80GB · United States

Available

from $1.35/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 3–8 min

Reliability: Good

Last checked: just now

A100 80GB · United States

Available

from $1.35/hr

Best for

LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct

Startup: 3–8 min

Reliability: High

Last checked: just now

Known limitations

  • GPTQ artifact existence, licence, quality, and runner compatibility have not been validated.

Related troubleshooting