internlm2-chat-20b
internlm2-chat-20b is an open-weight language model from Shanghai AI Lab (InternLM) with 19.9B parameters. At 4-bit it needs about 14.9 GB of memory, so the smallest current device that fits it is the Arc Pro B60.
Overview
Includes room for an 8k context and runtime overhead. More context needs more memory.
Key information
- Lab
- Shanghai AI Lab (InternLM)
- Released
- 10 Jan 2024
- Parameters
- 19.9B
- Type
- Language
- Context
- 32,768 tokens
- License
- Custom license
- HF downloads, 30 days
- 22,577
- Repository
- internlm/internlm2-chat-20b
More from Shanghai AI Lab (InternLM)
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 14.9 GB |
| Q8 | 24.9 GB |
| BF16 | 45.5 GB |
| RTX 5060 Ti 16 GB | 16 GB usable |
| RTX 5090 32 GB | 32 GB usable |
| DGX Spark 128 GB | 108.8 GB usable |
| Mac Studio M5 Ultra 256 GB | 192 GB usable |
Single-device memory estimate. Pick a device to update the On your device column.
36 GB usable memory
| Format | Memory needed | On your device | Example hardware |
|---|---|---|---|
| 4-bit (Q4) | ≈ 14.9 GB | Fits 41% | Arc Pro B6024 GB memory |
| 8-bit (Q8) | ≈ 24.9 GB | Fits 69% | Radeon AI PRO R970032 GB memory |
| 16-bit (BF16) | ≈ 45.5 GB | Too big 126% | A100 80GB SXM80 GB memory |
Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.
Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.
Where to run it
Through an API
No hosted API found.
More about this model
Frequently asked questions
How much memory does internlm2-chat-20b need? At an 8k context, about 14.9 GB at 4-bit, 24.9 GB at 8-bit and 45.5 GB at 16-bit (BF16). A longer context needs more.
Can I run internlm2-chat-20b on a Mac? The smallest current Mac that fits the 4-bit estimate of 14.9 GB is the Mac mini M6 (32GB). We have not found a trusted MLX or GGUF build yet.
Does the full context fit? internlm2-chat-20b supports up to 32,768 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.
What does it cost through an API? We did not find a hosted API for this model.
License in plain English
Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.
OMHQ RigBench
Not yet tested. We show no speed or quality score without a measurement.
Revision history and sources
Last updated . Sources:Hugging Face model card.