Internlm 20B vs Internlm2 5 7B Chat
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Internlm 20B | Internlm2 5 7B Chat | |
|---|---|---|
| Parameters | 20B | 7B |
| Context | 4K | 33K |
| Architecture | InternLMForCausalLM | InternLM2ForCausalLM |
| License | Apache 2.0 | Other |
| Downloads | 1.6K | 37.8K |
| Released | — | Mar 2025 |
VRAM by Quantization: Internlm 20B vs Internlm2 5 7B Chat
| Quantization | Bits | Internlm 20B VRAM | Internlm2 5 7B Chat VRAM |
|---|---|---|---|
| BF16 | 16.00 | 42.8 GB | 14.6 GB |
Verdict
Internlm2 5 7B Chat needs less VRAM at BF16 (14.6 GB vs 42.8 GB), so it fits on smaller GPUs. Internlm2 5 7B Chat supports a longer context window (33K tokens). Internlm2 5 7B Chat is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Internlm 20B or Internlm2 5 7B Chat?
At BF16, Internlm 20B needs 42.8 GB and Internlm2 5 7B Chat needs 14.6 GB, so Internlm2 5 7B Chat is the lighter option to run locally.
- Which has a longer context window, Internlm 20B or Internlm2 5 7B Chat?
Internlm 20B supports 4,096 tokens and Internlm2 5 7B Chat supports 32,768 tokens.
- What is the difference between Internlm 20B and Internlm2 5 7B Chat?
Internlm 20B is a 20B model from InternLM (InternLM family), while Internlm2 5 7B Chat is a 7B model from InternLM (InternLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.