Zamba2 7B Instruct on AMD Radeon RX 9070 XT

Can the AMD Radeon RX 9070 XT run Zamba2 7B Instruct?

71 pts

Yes, it runs well

Runs well. At Q8_0 it needs about 10.0 GB of 16.0 GB usable, with an estimated speed of 46.8 tok/s.

Best quant: Q8_0
Generation speed: 46.8 tok/s
Prompt processing: 8,196 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 4K

Download Zamba2 7B Instruct

Original weights · Hugging Face

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

huggingface.co/Zyphra/Zamba2-7B-Instruct (opens in a new tab)

No sign-in needed.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the B 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.	17.1 / 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.	14.4 / 15
Total	71.5 / 100	71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15

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

Every quantization on the AMD Radeon RX 9070 XT

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	5.1 GB	16.0 GB	151 tok/s	Runs well	59 ptsGood (B) · 59 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.4/15	All files (opens in a new tab)
`Q3_K_M`	5.8 GB	16.0 GB	119 tok/s	Runs well	62 ptsGood (B) · 62 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.3/15	All files (opens in a new tab)
`Q4_K_M`	6.7 GB	16.0 GB	91.9 tok/s	Runs well	65 ptsGood (B) · 65 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.6/15	All files (opens in a new tab)
`Q5_K_M`	7.4 GB	16.0 GB	75.9 tok/s	Runs well	67 ptsGood (B) · 67 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15	All files (opens in a new tab)
`Q6_K`	8.2 GB	16.0 GB	63.8 tok/s	Runs well	68 ptsGood (B) · 68 of 100 points: Model quality 16.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15	All files (opens in a new tab)
`Q8_0`	10.0 GB	16.0 GB	46.8 tok/s	Runs well	71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15	All files (opens in a new tab)
`F16`	16.9 GB	16.0 GB	15.0 tok/s	Runs with offload	51 ptsUsable (C) · 51 of 100 points: Model quality 17.1/45, Memory fit 10.0/25, Speed 9.2/15, Memory use 15.0/15	Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

72 ptsGreat (A) · 72 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 SUPER Q8_0 · 42.8 tok/s
71 ptsGood (B) · 71 of 100 points: Model quality 16.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Intel Arc B580 Q6_K · 40.3 tok/s
71 ptsGood (B) · 71 of 100 points: Model quality 16.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3060 12GB Q6_K · 41.7 tok/s
71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 57.1 tok/s
71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 NVIDIA GeForce RTX 4080 SUPER Q8_0 · 62.5 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.