on

Can the Apple M6 (16 GB) run Jamba2 3B?

40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q5_K_M it needs about 3.6 GB of 10.7 GB usable, with an estimated speed of 44.1 tok/s.

Best quant
Q5_K_M
Generation speed
44.1 tok/s
Prompt processing
1,166 tok/s
First token (1K prompt)
0.9 s
Largest safe context
256K

Best app to run it on the Apple M6 (16 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Jamba2 3B in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

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 Jamba2 3B

Recommended for the Apple M6 (16 GB): Q5_K_M. 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 Q5_K_M 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:Q5_K_M

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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q5_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 great
How well it runs on the Apple M6 (16 GB): 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.18.3 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.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.7.8 / 15
Match score66.1 / 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 Apple M6 (16 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 2.7 GB 10.7 GB 87.7 tok/s Runs great 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 3.0 GB 10.7 GB 69.0 tok/s Runs great 35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 3.3 GB 10.7 GB 53.4 tok/s Runs great 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 3.6 GB 10.7 GB 44.1 tok/s Runs great 40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 4.0 GB 10.7 GB 37.0 tok/s Runs great 41Fair quality (C) · 41 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 4.7 GB 10.7 GB 27.2 tok/s Runs well 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 7.5 GB 10.7 GB 12.5 tok/s Runs well 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. 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

Quick answers

How much memory does Jamba2 3B need on the M6 16GB?

At Q5_K_M it needs about 3.6 GB. The M6 16GB has 10.7 GB usable.

How fast is Jamba2 3B on the M6 16GB?

About 44.1 tok/s at Q5_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Jamba2 3B should I use on the M6 16GB?

Q5_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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?