internlm3-8b-instruct
internlm/internlm3-8b-instruct
Official · BF16 · safetensors
Runtime certified: vLLM Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
InternLM · General · InternLM3
InternLM3 8B: Specs, GPU requirements, hosting & deployment
InternLM3 8B is a legacy General release in the InternLM family, certified from its immutable official source revision.
Total parameters8.0B
Active parametersDense model
Context window131,072 tokens
Release statusLegacy · Legacy
ArchitectureDense Transformer
ModalitiesText
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2025-01-13
Architecture, strengths and use cases
InternLM3 8B is an official self-hostable Shanghai AI Laboratory release in the InternLM General track. It uses Dense Transformer, carries 8B, supports a verified context window of 131,072 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
InternLM3 8B uses Dense Transformer with 8B. The stored architecture profile records 64 layers, hidden width 8192, 64 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Verified Dense Transformer architecture
131,072 token certified context
Official BF16, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed vllm, transformers runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory15.35 GB
KV cache2 GB
Runtime overhead7.84 GB
Total with safety margin31.24 GB
Recommended best value
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
109.76 GB headroom · Limited capacity
USD 2,345 / monthLowest-cost viable
2× NVIDIA L4 24GB
48 GB total VRAM · pcie
16.76 GB headroom · Available
USD 500 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
109.76 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The full 8B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
InternLM3 8B is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Release timeline
internlm/internlm/internlm3-8b @ 58930c5e0f2b0b2653149106bcb51a314d82a23711fe4dabdfd5d90f3cd33cb6
Frequently asked questions
How much VRAM does InternLM3 8B require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support InternLM3 8B?
Certified upstream runtime evidence is available for vllm, transformers.
Can InternLM3 8B be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26