Jamba 1.5 Mini on NVIDIA RTX 4000 SFF Ada Generation

Can the NVIDIA RTX 4000 SFF Ada Generation run Jamba 1.5 Mini?

Yes, it runs well (offloads to RAM)

Runs well (offloads to RAM). At Q3_K_M it needs about 27.0 GB of 20.0 GB usable, with an estimated speed of 18.5 tok/s.

Best quant: Q3_K_M
Generation speed: 18.5 tok/s
Prompt processing: 929 tok/s
First token (1K prompt): 1.1 s
Largest safe context: —

Best app to run it on the NVIDIA RTX 4000 SFF Ada Generation

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Jamba 1.5 Mini in LM Studio

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Jamba 1.5 Mini in LM Studio

llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

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 Jamba 1.5 Mini

Recommended for the NVIDIA RTX 4000 SFF Ada Generation: Q3_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 Q3_K_M file (opens in a new tab)

huggingface.co/mradermacher/AI21-Jamba-Mini-1.5-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/AI21-Jamba-Mini-1.5-i1-GGUF:Q3_K_M

Original weights · Hugging Face

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

huggingface.co/ai21labs/AI21-Jamba-Mini-1.5 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (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 welloffloads to RAM: How well it runs on the NVIDIA RTX 4000 SFF Ada Generation: 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.	18.9 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	10.2 / 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	54.1 / 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 NVIDIA RTX 4000 SFF Ada Generation

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	22.4 GB	20.0 GB	31.1 tok/s	Runs welloffloads to RAM	35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	27.0 GB	20.0 GB	18.5 tok/s	Runs welloffloads to RAM	42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	33.2 GB	20.0 GB	11.7 tok/s	Slowheavy RAM offload	47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	38.3 GB	20.0 GB	8.8 tok/s	Slowheavy RAM offload	48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	44.0 GB	20.0 GB	—	Won't run	49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	56.4 GB	20.0 GB	—	Won't run	50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	105 GB	20.0 GB	—	Won't run	50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 6/100 (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

50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 68.9 tok/s · Runs great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 41.4 tok/s · Runs great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q4_K_M · 31.5 tok/s · Runs great
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q3_K_M · 134 tok/s · Runs well (tight fit)
47Fair quality (C) · 47 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. Apple M4 Pro (48 GB) Q4_K_M · 22.2 tok/s · Runs well (tight fit)
49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q6_K · 41.6 tok/s · Runs great

Quick answers

How much memory does Jamba 1.5 Mini need on the NVIDIA RTX 4000 SFF Ada Generation 20GB?

At Q3_K_M it needs about 27.0 GB. The NVIDIA RTX 4000 SFF Ada Generation 20GB has 20.0 GB usable.

How fast is Jamba 1.5 Mini on the NVIDIA RTX 4000 SFF Ada Generation 20GB?

About 18.5 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Jamba 1.5 Mini should I use on the NVIDIA RTX 4000 SFF Ada Generation 20GB?

Q3_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.