Check my GPU

on

Can the NVIDIA RTX 2000 Ada Generation Laptop GPU run TMax 4B?

80 ptsGreat (A) · 80 of 100 points: Model quality 27.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15

Yes, it runs well

Runs well. At Q6_K it needs about 4.7 GB of 8.0 GB usable, with an estimated speed of 51.8 tok/s.

Best quant
Q6_K
Generation speed
51.8 tok/s
Prompt processing
2,480 tok/s
First token (1K prompt)
0.4 s
Largest safe context
105K

Download TMax 4B

Original weights · Hugging Face

Full-precision files from Ai2, for fine-tuning, vLLM, Transformers.

huggingface.co/allenai/tmax-4b (opens in a new tab)

No sign-in needed.

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the A 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.27.2 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.25.0 / 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.13.6 / 15
Total80.8 / 10080 ptsGreat (A) · 80 of 100 points: Model quality 27.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15

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

Every quantization on the NVIDIA RTX 2000 Ada Generation Laptop GPU

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 3.0 GB 8.0 GB 123 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15 All files (opens in a new tab)
Q3_K_M 3.3 GB 8.0 GB 96.5 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.6/15 All files (opens in a new tab)
Q4_K_M 3.8 GB 8.0 GB 74.6 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15 All files (opens in a new tab)
Q5_K_M 4.3 GB 8.0 GB 61.7 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 26.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15 All files (opens in a new tab)
Q6_K 4.7 GB 8.0 GB 51.8 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 27.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15 All files (opens in a new tab)
Q8_0 5.7 GB 8.0 GB 38.0 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.5/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 15.0/15 All files (opens in a new tab)
F16 9.7 GB 8.0 GB 11.2 tok/s Runs with offload 60 ptsGood (B) · 60 of 100 points: Model quality 27.5/45, Memory fit 10.0/25, Speed 7.9/15, Memory use 15.0/15 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.