LLMs ·

TMax 27B

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.

Apps that run TMax 27B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically up to 10% faster than GGUF for a model with 27.4B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App Type Opens it as Systems Engine Start
LM Studio Desktop app MLX macOSWindowsLinux llama.cpp, MLX Open in LM Studio
Jan Desktop app MLX macOSWindowsLinux llama.cpp, MLX Get Jan
MLX LM CLI + API MLX macOS MLX 
mlx_lm.chat --model mlx-community/Tmax-27B-MLX-4bit
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve allenai/tmax-27b
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path allenai/tmax-27b
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/allenai/tmax-27b
Unsloth Desktop Desktop app MLX macOSWindowsLinux llama.cpp, MLX, stable-diffusion.cpp Get Unsloth Desktop
Atomic Chat Desktop app MLX macOSWindowsLinux llama.cpp, MLX-VLM Open in Atomic Chat
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI
Msty Studio Desktop app MLX macOSWindowsLinux Ollama, llama.cpp, MLX Get Msty Studio
Inferencer Desktop app MLX macOS MLX Get Inferencer
exo Server MLX macOSLinux MLX Get exo

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

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

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.

Quality Hardware Quant Memory Speed Runs
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Founders EditionNVIDIA GeForce RTX 5090 Q6_K 25.2 GB / 32.0 GB 55.8 tok/s Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. ASUS ROG Strix GeForce RTX 3090 OC Edition 24GB GDDR6XNVIDIA GeForce RTX 3090 Q4_K_M 19.0 GB / 24.0 GB 42.0 tok/s Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Founders EditionNVIDIA GeForce RTX 4090 Q4_K_M 19.0 GB / 24.0 GB 45.2 tok/s Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 7900 XTX Vapor-X 24GBAMD Radeon RX 7900 XTX Q4_K_M 19.0 GB / 24.0 GB 37.1 tok/s Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell Q8_0 34.9 GB / 96.0 GB 40.9 tok/s Runs great
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPERNVIDIA GeForce RTX 4080 SUPER Q3_K_M 15.3 GB / 16.0 GB 42.7 tok/s Runs welltight fit
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. ASUS TUF Gaming GeForce RTX 5070 Ti 16GB GDDR7 OC EditionNVIDIA GeForce RTX 5070 Ti Q3_K_M 15.3 GB / 16.0 GB 52.0 tok/s Runs welltight fit
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Founders EditionNVIDIA GeForce RTX 5080 Q3_K_M 15.3 GB / 16.0 GB 55.7 tok/s Runs welltight fit
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 4070 Ti SUPER Q3_K_M 15.3 GB / 16.0 GB 39.0 tok/s Runs welltight fit
75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 9070 XT OCAMD Radeon RX 9070 XT Q3_K_M 15.3 GB / 16.0 GB 32.0 tok/s Runs welltight fit

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.

Was this page helpful?