Check my GPU

LLMs ·

InternLM2 Math Plus 20B

Parameters
20B
Architecture
Dense
Max context
8K tokens
License
internlm
Released
2024-05

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/bartowski/internlm2-math-plus-20b-GGUF (opens in a new tab)

ollama run hf.co/bartowski/internlm2-math-plus-20b-GGUF

Original weights · Hugging Face

Full-precision files from Shanghai AI Lab, for fine-tuning, vLLM, Transformers.

huggingface.co/internlm/internlm2-math-plus-20b (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Download
Q2_K Low 7.9 GB 10.2 GB GGUF (opens in a new tab)
Q3_K_M Low 9.7 GB 11.9 GB GGUF (opens in a new tab)
Q4_K_M Good 12.1 GB 14.3 GB GGUF (opens in a new tab)
Q5_K_M High 14.1 GB 16.3 GB GGUF (opens in a new tab)
Q6_K High 16.3 GB 18.5 GB GGUF (opens in a new tab)
Q8_0 Very high 21.1 GB 23.3 GB GGUF (opens in a new tab)
F16 Full 39.7 GB 41.9 GB Original weights (opens in a new tab)

Best hardware for InternLM2 Math Plus 20B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B580 (launch price $249) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q8_0 24.9 GB / 32.0 GB 56.4 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q6_K 19.7 GB / 24.0 GB 40.1 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q6_K 19.7 GB / 24.0 GB 43.2 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q5_K_M 17.5 GB / 24.0 GB 42.2 tok/s Runs well
71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q4_K_M 15.1 GB / 16.0 GB 41.5 tok/s Tight fit
71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q4_K_M 15.1 GB / 16.0 GB 45.5 tok/s Tight fit
71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q4_K_M 15.1 GB / 16.0 GB 55.4 tok/s Tight fit
71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q4_K_M 15.1 GB / 16.0 GB 59.3 tok/s Tight fit
70 ptsGood (B) · 70 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q3_K_M 12.7 GB / 16.0 GB 44.0 tok/s Runs well
69 ptsGood (B) · 69 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 15.0/15 NVIDIA GeForce RTX 5060 Ti 16GB Q3_K_M 12.7 GB / 16.0 GB 35.8 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.