LLMs · Ai2

TMax 27B

Name: TMax 27B
Author: Ai2

Parameters: 27B
Architecture: Dense
Max context: 256K tokens
License: apache-2.0
Released: 2026-06

How to run it

Original weights · Hugging Face

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

huggingface.co/allenai/tmax-27b (opens in a new tab)

No sign-in needed.

Links checked 6 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.

KV cache: hybrid: only the full-attention layers (1 in 4) keep a KV cache; the rest use linear attention.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	10.9 GB	12.1 GB	13.7 GB	All files (opens in a new tab)
`Q3_K_M`	Low	13.4 GB	14.5 GB	16.2 GB	All files (opens in a new tab)
`Q4_K_M`	Good	16.7 GB	17.8 GB	19.4 GB	All files (opens in a new tab)
`Q5_K_M`	High	19.4 GB	20.6 GB	22.2 GB	All files (opens in a new tab)
`Q6_K`	High	22.4 GB	23.6 GB	25.2 GB	All files (opens in a new tab)
`Q8_0`	Very high	29.0 GB	30.1 GB	31.7 GB	All files (opens in a new tab)
`F16`	Full	54.7 GB	55.9 GB	57.5 GB	Original weights (opens in a new tab)

Best hardware for TMax 27B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at Q3_K_M.

Grade · points	Hardware	Quant	Memory	Speed	Fit
95 ptsExcellent (S) · 95 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5090	`Q6_K`	25.2 GB / 32.0 GB	55.8 tok/s	Runs well
93 ptsExcellent (S) · 93 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 3090	`Q4_K_M`	19.0 GB / 24.0 GB	42.0 tok/s	Runs well
93 ptsExcellent (S) · 93 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4090	`Q4_K_M`	19.0 GB / 24.0 GB	45.2 tok/s	Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 15.0/15	AMD Radeon RX 7900 XTX	`Q4_K_M`	19.0 GB / 24.0 GB	37.1 tok/s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 40.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15	NVIDIA RTX PRO 6000 Blackwell	`Q8_0`	34.9 GB / 96.0 GB	40.9 tok/s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4080 SUPER	`Q3_K_M`	15.3 GB / 16.0 GB	42.7 tok/s	Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5070 Ti	`Q3_K_M`	15.3 GB / 16.0 GB	52.0 tok/s	Tight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5080	`Q3_K_M`	15.3 GB / 16.0 GB	55.7 tok/s	Tight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 34.0/45, Memory fit 24.0/25, Speed 14.8/15, Memory use 15.0/15	NVIDIA GeForce RTX 4070 Ti SUPER	`Q3_K_M`	15.3 GB / 16.0 GB	39.0 tok/s	Tight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 15.0/15	Apple M4 Pro (48 GB)	`Q6_K`	26.5 GB / 36.0 GB	7.3 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.