Can the AMD Radeon RX 9070 XT run Jamba2 3B?

69 pts

Yes, it runs well

Runs well. At F16 it needs about 7.5 GB of 16.0 GB usable, with an estimated speed of 52.4 tok/s.

Best quant: F16
Generation speed: 52.4 tok/s
Prompt processing: 19,910 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Download Jamba2 3B

Recommended for the AMD Radeon RX 9070 XT: F16. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the F16 file (opens in a new tab)

huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF:BF16

Original weights · Hugging Face

Full-precision files from AI21 Labs, for fine-tuning, vLLM, Transformers.

huggingface.co/ai21labs/AI21-Jamba2-3B (opens in a new tab)

No sign-in needed.

Links checked 6 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.	18.9 / 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.	10.8 / 15
Total	69.7 / 100	69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15

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`	2.6 GB	16.0 GB	367 tok/s	Runs well	57 ptsUsable (C) · 57 of 100 points: Model quality 13.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	GGUF (opens in a new tab)
`Q3_K_M`	2.9 GB	16.0 GB	289 tok/s	Runs well	60 ptsGood (B) · 60 of 100 points: Model quality 15.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15	GGUF (opens in a new tab)
`Q4_K_M`	3.3 GB	16.0 GB	223 tok/s	Runs well	62 ptsGood (B) · 62 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15	GGUF (opens in a new tab)
`Q5_K_M`	3.6 GB	16.0 GB	184 tok/s	Runs well	63 ptsGood (B) · 63 of 100 points: Model quality 18.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15	GGUF (opens in a new tab)
`Q6_K`	3.9 GB	16.0 GB	155 tok/s	Runs well	64 ptsGood (B) · 64 of 100 points: Model quality 18.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15	GGUF (opens in a new tab)
`Q8_0`	4.6 GB	16.0 GB	114 tok/s	Runs well	65 ptsGood (B) · 65 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15	GGUF (opens in a new tab)
`F16`	7.5 GB	16.0 GB	52.4 tok/s	Runs well	69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15	GGUF (opens in a new tab) 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

72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15 NVIDIA GeForce RTX 4070 SUPER F16 · 47.9 tok/s
71 ptsGood (B) · 71 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.2/15 NVIDIA GeForce RTX 4060 Q8_0 · 56.1 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 4070 Ti SUPER F16 · 63.9 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 4080 SUPER F16 · 70.0 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 NVIDIA GeForce RTX 5060 Ti 16GB F16 · 42.6 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.