Can the NVIDIA GeForce RTX 5090 run TMax 9B?

87 pts

Yes, it runs well

Runs well. At F16 it needs about 20.4 GB of 32.0 GB usable, with an estimated speed of 57.7 tok/s.

Best quant: F16
Generation speed: 57.7 tok/s
Prompt processing: 8,431 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Download TMax 9B

Original weights · Hugging Face

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

huggingface.co/allenai/tmax-9b (opens in a new tab)

No sign-in needed.

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

How the S 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.	33.3 / 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.	14.7 / 15
Total	88.0 / 100	87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.7/15

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

Every quantization on the NVIDIA GeForce RTX 5090

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	6.0 GB	32.0 GB	404 tok/s	Runs well	67 ptsGood (B) · 67 of 100 points: Model quality 23.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15	All files (opens in a new tab)
`Q3_K_M`	6.9 GB	32.0 GB	318 tok/s	Runs well	72 ptsGreat (A) · 72 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15	All files (opens in a new tab)
`Q4_K_M`	7.9 GB	32.0 GB	246 tok/s	Runs well	77 ptsGreat (A) · 77 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15	All files (opens in a new tab)
`Q5_K_M`	8.8 GB	32.0 GB	203 tok/s	Runs well	78 ptsGreat (A) · 78 of 100 points: Model quality 32.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15	All files (opens in a new tab)
`Q6_K`	9.8 GB	32.0 GB	171 tok/s	Runs well	80 ptsGreat (A) · 80 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15	All files (opens in a new tab)
`Q8_0`	12.0 GB	32.0 GB	125 tok/s	Runs well	81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15	All files (opens in a new tab)
`F16`	20.4 GB	32.0 GB	57.7 tok/s	Runs well	87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.7/15	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

88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 46.9 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q8_0 · 51.4 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q8_0 · 62.6 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q8_0 · 67.0 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q8_0 · 38.5 tok/s

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.