Skip to content

Internlm2 5 7B Chat VRAM requirements

How much VRAM Internlm2 5 7B Chat needs
4-bit weights: 4.4 GBWith 8K context: 6.1 GBWith 32K context: 9.1 GB8-bit, 8K context: 9.4 GB
Parameters
7.7B
Longest context
32K
Released
Jun 2024
License
Custom
Strongest at
Not rated

Its licence (Custom) is not a standard open-source one: check the terms before commercial use.

How much VRAM Internlm2 5 7B Chat needs

Memory Internlm2 5 7B Chat needs at each precision and context length
PrecisionWeightsWith 8KWith 32K
16-bit14.4 GB16.2 GB19.2 GB
8-bit7.7 GB9.4 GB12.4 GB
6-bit5.9 GB7.7 GB10.7 GB
5-bit5.1 GB6.9 GB9.9 GB
4-bit4.4 GB6.1 GB9.1 GB
3-bit3.5 GB5.3 GB8.3 GB
2-bit2.7 GB4.5 GB7.5 GB
1.6-bit1.5 GB3.2 GB6.2 GB

One conversation, 16-bit context cache, runtime overhead included.

GPUs and Macs that run Internlm2 5 7B Chat

The best way Internlm2 5 7B Chat runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 40604-bit16K41 tok/s1.0 sPDF: Internlm2 5 7B Chat on RTX 4060 report
RTX 50604-bit16K66 tok/s0.8 sPDF: Internlm2 5 7B Chat on RTX 5060 report
RTX 30704-bit16K66 tok/s0.8 sPDF: Internlm2 5 7B Chat on RTX 3070 report
RTX 3080 10 GB6-bit20K81 tok/s0.5 sPDF: Internlm2 5 7B Chat on RTX 3080 10 GB report
RTX 3060 12 GB8-bit20K31 tok/s1.2 sPDF: Internlm2 5 7B Chat on RTX 3060 12 GB report
Arc B5808-bit20K28 tok/s0.8 sPDF: Internlm2 5 7B Chat on Arc B580 report
RTX 40708-bit20K43 tok/s0.5 sPDF: Internlm2 5 7B Chat on RTX 4070 report
RTX 4070 Super8-bit20K43 tok/s0.4 sPDF: Internlm2 5 7B Chat on RTX 4070 Super report
RTX 50708-bit20K57 tok/s0.5 sPDF: Internlm2 5 7B Chat on RTX 5070 report
RTX 4060 Ti 16 GB8-bit32K25 tok/s0.7 sPDF: Internlm2 5 7B Chat on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GB8-bit32K39 tok/s0.7 sPDF: Internlm2 5 7B Chat on RTX 5060 Ti 16 GB report
Arc A770 16 GB8-bit32K34 tok/s0.8 sPDF: Internlm2 5 7B Chat on Arc A770 16 GB report
Radeon RX 9070 XT8-bit32K46 tok/s0.4 sPDF: Internlm2 5 7B Chat on Radeon RX 9070 XT report
RTX 4070 Ti Super8-bit32K57 tok/s0.4 sPDF: Internlm2 5 7B Chat on RTX 4070 Ti Super report
RTX 4080 Super8-bit32K62 tok/s0.3 sPDF: Internlm2 5 7B Chat on RTX 4080 Super report
RTX 5070 Ti8-bit32K74 tok/s0.4 sPDF: Internlm2 5 7B Chat on RTX 5070 Ti report
RTX 50808-bit32K79 tok/s0.3 sPDF: Internlm2 5 7B Chat on RTX 5080 report
Radeon RX 7900 XTX8-bit32K66 tok/s0.7 sPDF: Internlm2 5 7B Chat on Radeon RX 7900 XTX report
RTX 30908-bit32K78 tok/s0.4 sPDF: Internlm2 5 7B Chat on RTX 3090 report
RTX 40908-bit32K83 tok/s0.2 sPDF: Internlm2 5 7B Chat on RTX 4090 report
Radeon AI PRO R97008-bit32K46 tok/s0.4 sPDF: Internlm2 5 7B Chat on Radeon AI PRO R9700 report
RTX 50908-bit32K139 tok/s0.1 sPDF: Internlm2 5 7B Chat on RTX 5090 report
2× RTX 30908-bit32K78 tok/s0.3 sPDF: Internlm2 5 7B Chat on 2× RTX 3090 report
2× RTX 40908-bit32K83 tok/s0.1 sPDF: Internlm2 5 7B Chat on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GB8-bit32K108 tok/s0.2 sPDF: Internlm2 5 7B Chat on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada8-bit32K79 tok/s0.2 sPDF: Internlm2 5 7B Chat on RTX 6000 Ada report
L40S8-bit32K72 tok/s0.3 sPDF: Internlm2 5 7B Chat on L40S report
2× RTX 50908-bit32K139 tok/s0.1 sPDF: Internlm2 5 7B Chat on 2× RTX 5090 report
4× RTX 30908-bit32K78 tok/s0.1 sPDF: Internlm2 5 7B Chat on 4× RTX 3090 report
RTX PRO 6000 Blackwell8-bit32K139 tok/s0.1 sPDF: Internlm2 5 7B Chat on RTX PRO 6000 Blackwell report
Mac mini M4 16 GB6-bit28K16 tok/s9.9 sPDF: Internlm2 5 7B Chat on Mac mini M4 16 GB report
Mac mini M4 24 GB8-bit32K12 tok/s9.9 sPDF: Internlm2 5 7B Chat on Mac mini M4 24 GB report
Mac mini M4 32 GB8-bit32K12 tok/s9.9 sPDF: Internlm2 5 7B Chat on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GB8-bit32K27 tok/s5.0 sPDF: Internlm2 5 7B Chat on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit32K27 tok/s5.0 sPDF: Internlm2 5 7B Chat on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit32K27 tok/s5.0 sPDF: Internlm2 5 7B Chat on Mac mini M4 Pro 64 GB report
M4 Max 128 GB8-bit32K46 tok/s2.5 sPDF: Internlm2 5 7B Chat on M4 Max 128 GB report
M5 Max 128 GB8-bit32K51 tok/s0.7 sPDF: Internlm2 5 7B Chat on M5 Max 128 GB report
M3 Ultra 96 GB8-bit32K58 tok/s1.4 sPDF: Internlm2 5 7B Chat on M3 Ultra 96 GB report
M3 Ultra 256 GB8-bit32K58 tok/s1.4 sPDF: Internlm2 5 7B Chat on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit32K58 tok/s1.4 sPDF: Internlm2 5 7B Chat on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit32K79 tok/s0.4 sPDF: Internlm2 5 7B Chat on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit32K19 tok/s1.4 sPDF: Internlm2 5 7B Chat on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB8-bit32K19 tok/s1.4 sPDF: Internlm2 5 7B Chat on Ryzen AI Max+ 395 128 GB report
RTX Spark8-bit32K26 tok/s0.5 sPDF: Internlm2 5 7B Chat on RTX Spark report
DGX Spark8-bit32K24 tok/s0.5 sPDF: Internlm2 5 7B Chat on DGX Spark report
Dual DGX Spark8-bit32K24 tok/s0.3 sPDF: Internlm2 5 7B Chat on Dual DGX Spark report
DGX Station GB3008-bit32K395 tok/s0.1 sPDF: Internlm2 5 7B Chat on DGX Station GB300 report
2× RTX PRO 6000 Blackwell8-bit32K139 tok/s0.1 sPDF: Internlm2 5 7B Chat on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit32K139 tok/s0.1 sPDF: Internlm2 5 7B Chat on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit32K139 tok/s0.1 sPDF: Internlm2 5 7B Chat on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXM8-bit32K155 tok/s0.3 sPDF: Internlm2 5 7B Chat on A100 80 GB SXM report
H100 SXM8-bit32K233 tok/s0.1 sPDF: Internlm2 5 7B Chat on H100 SXM report
4× H200 NVL8-bit32K304 tok/s0.1 sPDF: Internlm2 5 7B Chat on 4× H200 NVL report
8× H200 NVL8-bit32K304 tok/s0.1 sPDF: Internlm2 5 7B Chat on 8× H200 NVL report

Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.

How to run it

llama.cpp
llama-server -hf Slipstream-Max/Emollm-InternLM2.5-7B-chat-GGUF-fp16
vLLM
vllm serve internlm/internlm2_5-7b-chat

Questions

How much VRAM does Internlm2 5 7B Chat need?

Internlm2 5 7B Chat needs 4.4 GB for its weights at 4-bit, 6.1 GB with an 8K context and 9.1 GB with 32K. At 8-bit, 9.4 GB.

What is the minimum VRAM for Internlm2 5 7B Chat?

About 5.3 GB at 3-bit with an 8K context, the lowest precision we recommend for a model this size. The smallest machine here that runs it without spilling is the RTX 4060.

How big is Internlm2 5 7B Chat?

7.7B parameters: 14.4 GB of weights at 16-bit, 4.4 GB at 4-bit.

Can Internlm2 5 7B Chat run on an RTX 4090?

Yes. At 8-bit it holds 32K of context and writes about 83 tokens a second.

More models