Dolphin 3.0 Llama 3.1 8B on Intel Celeron J3455 / N3450 (Apollo Lake) NAS (8 GB)

Can the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (8 GB) run Dolphin 3.0 Llama 3.1 8B?

Barely: it runs very slowly (over memory limit)

Very slow (over memory limit). At Q2_K it needs about 5.3 GB of 5.2 GB usable, with an estimated speed of 0.9 tok/s.

Best quant: Q2_K
Generation speed: 0.9 tok/s
Prompt processing: 0.7 tok/s
First token (1K prompt): 1,370.5 s
Largest safe context: 7K

Best app to run it on the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (8 GB)

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

Splits the model between GPU memory and system RAM, which this setup needs.
One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run dolphin3:8b

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

Want an agent? Dolphin 3.0 Llama 3.1 8B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download Dolphin 3.0 Llama 3.1 8B

Recommended for the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (8 GB): Q2_K. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run dolphin3:8b

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

huggingface.co/dphn/Dolphin3.0-Llama3.1-8B-GGUF (opens in a new tab)

ollama run hf.co/dphn/Dolphin3.0-Llama3.1-8B-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/dphn/Dolphin3.0-Llama3.1-8B (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 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 Very slowover memory limit: How well it runs on the Intel Celeron J3455 / N3450 (Apollo Lake) NAS (8 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.	14.5 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); fewer when it goes past that limit.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	2.2 / 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	41.7 / 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 Celeron J3455 / N3450 (Apollo Lake) NAS (8 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.3 GB	5.2 GB	0.9 tok/s	Very slowover memory limit	32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	6.0 GB	5.2 GB	0.7 tok/s	Very slowfar over memory limit	38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	7.0 GB	5.2 GB	—	Won't run	43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	7.8 GB	5.2 GB	—	Won't run	44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	8.7 GB	5.2 GB	—	Won't run	45Fair quality (C) · 45 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`	10.6 GB	5.2 GB	—	Won't run	46Fair quality (C) · 46 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 (opens in a new tab)
`F16`	18.1 GB	5.2 GB	—	Won't run	46Fair quality (C) · 46 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.	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

46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 42.9 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 52.3 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 57.3 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 69.7 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 74.7 tok/s · Runs great
45Fair quality (C) · 45 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q6_K · 53.5 tok/s · Runs great

Quick answers

How much memory does Dolphin 3.0 Llama 3.1 8B need on the Intel Celeron J3455 / N3450 (Apollo Lake) NAS 8GB?

At Q2_K it needs about 5.3 GB. The Intel Celeron J3455 / N3450 (Apollo Lake) NAS 8GB has 5.2 GB usable.

How fast is Dolphin 3.0 Llama 3.1 8B on the Intel Celeron J3455 / N3450 (Apollo Lake) NAS 8GB?

About 0.9 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Dolphin 3.0 Llama 3.1 8B should I use on the Intel Celeron J3455 / N3450 (Apollo Lake) NAS 8GB?

Q2_K. 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.