Can the Intel Arc A770 16GB run TMax 27B?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q3_K_M it needs about 15.3 GB of 16.0 GB usable, with an estimated speed of 24.8 tok/s.

Best quant: Q3_K_M
Generation speed: 24.8 tok/s
Prompt processing: 790 tok/s
First token (1K prompt): 1.3 s
Largest safe context: 17K

Best app to run it on the Intel Arc A770 16GB

On Windows

Command line + local API · runs on llama.cpp, vLLM

Handy if you already work in Docker.

docker model run hf.co/allenai/tmax-27b

Text Generation WebUI

On Linux

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

Handy if you already work in Docker.

docker model run hf.co/allenai/tmax-27b

Text Generation WebUI

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download TMax 27B

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 5 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs welltight fit: How well it runs on the Intel Arc A770 16GB: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	34.0 / 45
Memory fitFull marks when everything sits in GPU 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.	11.8 / 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
Match score	84.8 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Intel Arc A770 16GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	12.9 GB	16.0 GB	31.5 tok/s	Runs great	63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	15.3 GB	16.0 GB	24.8 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 84/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	18.6 GB	16.0 GB	10.4 tok/s	Runs welloffloads to RAM	85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	21.4 GB	16.0 GB	6.4 tok/s	Slowoffloads to RAM	87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	24.4 GB	16.0 GB	4.4 tok/s	Slowheavy RAM offload	89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	30.9 GB	16.0 GB	2.6 tok/s	Very slowheavy RAM offload	90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	56.7 GB	16.0 GB	—	Won't run	90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	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

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 Q6_K · 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. NVIDIA GeForce RTX 3090 Q4_K_M · 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 Q4_K_M · 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. AMD Radeon RX 7900 XTX Q4_K_M · 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 Q8_0 · 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 SUPER Q3_K_M · 42.7 tok/s · Runs well (tight fit)

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.