Check my GPU

on

Can the NVIDIA GeForce RTX 4070 SUPER run InternLM2 Math Plus 20B?

66 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q2_K it needs about 10.8 GB of 12.0 GB usable, with an estimated speed of 51.2 tok/s.

Best quant
Q2_K
Generation speed
51.2 tok/s
Prompt processing
1,287 tok/s
First token (1K prompt)
0.8 s
Largest safe context
8K

Download InternLM2 Math Plus 20B

Recommended for the NVIDIA GeForce RTX 4070 SUPER: Q2_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

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

ollama run hf.co/bartowski/internlm2-math-plus-20b-GGUF:Q2_K

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 1 week ago against Hugging Face, Ollama and GitHub.

How the B grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.12.6 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Total66.6 / 10066 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 4070 SUPER

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 10.8 GB 12.0 GB 51.2 tok/s Tight fit 66 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q3_K_M 12.5 GB 12.0 GB 29.5 tok/s Runs with offload 53 ptsUsable (C) · 53 of 100 points: Model quality 15.1/45, Memory fit 10.0/25, Speed 12.9/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q4_K_M 14.9 GB 12.0 GB 12.1 tok/s Runs with offload 50 ptsUsable (C) · 50 of 100 points: Model quality 17.1/45, Memory fit 10.0/25, Speed 8.2/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 16.9 GB 12.0 GB 7.8 tok/s Heavy offload 43 ptsUsable (C) · 43 of 100 points: Model quality 17.5/45, Memory fit 4.0/25, Speed 6.6/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 19.1 GB 12.0 GB 5.6 tok/s Heavy offload 42 ptsUsable (C) · 42 of 100 points: Model quality 17.8/45, Memory fit 4.0/25, Speed 5.6/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 23.9 GB 12.0 GB 3.4 tok/s Heavy offload 41 ptsPoor (D) · 41 of 100 points: Model quality 18.0/45, Memory fit 4.0/25, Speed 4.4/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 42.5 GB 12.0 GB — Won't run 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

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.