SmolLM2 360M Instruct on AMD Ryzen 7 8845HS / Ryzen 7 255 NAS (96 GB)

Can the AMD Ryzen 7 8845HS / Ryzen 7 255 NAS (96 GB) run SmolLM2 360M Instruct?

Yes, it runs great

Runs great. At F16 it needs about 5.5 GB of 48.0 GB usable, with an estimated speed of 79.6 tok/s.

Best quant: F16
Generation speed: 79.6 tok/s
Prompt processing: 36,889 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 8K

Best app to run it on the AMD Ryzen 7 8845HS / Ryzen 7 255 NAS (96 GB)

On Linux

Ollama

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

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 smollm2:360m-instruct-fp16

llama.cpp Usually the first to support new model architectures.
KoboldCpp

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 SmolLM2 360M Instruct

Recommended for the AMD Ryzen 7 8845HS / Ryzen 7 255 NAS (96 GB): F16. 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 smollm2:360m-instruct-fp16

Quantized files · GGUF

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

huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct-GGUF (opens in a new tab)

ollama run hf.co/HuggingFaceTB/SmolLM2-360M-Instruct-GGUF

Original weights · Hugging Face

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

huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Hugging Face. The weights themselves download from Hugging Face.

github.com/huggingface/smollm (opens in a new tab)

git clone https://github.com/huggingface/smollm

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

How it’s rated

Quality 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, 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 AMD Ryzen 7 8845HS / Ryzen 7 255 NAS (96 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.	3.6 / 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.	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.	2.6 / 15
Match score	46.2 / 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 AMD Ryzen 7 8845HS / Ryzen 7 255 NAS (96 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	4.9 GB	48.0 GB	558 tok/s	Runs great	5Basic quality (D) · 5 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	5.0 GB	48.0 GB	439 tok/s	Runs great	6Basic quality (D) · 6 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.
`Q4_K_M`	5.0 GB	48.0 GB	339 tok/s	Runs great	7Basic quality (D) · 7 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.
`Q5_K_M`	5.0 GB	48.0 GB	280 tok/s	Runs great	7Basic quality (D) · 7 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.
`Q6_K`	5.1 GB	48.0 GB	236 tok/s	Runs great	7Basic quality (D) · 7 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.
`Q8_0`	5.2 GB	48.0 GB	173 tok/s	Runs great	8Basic quality (D) · 8 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	5.5 GB	48.0 GB	79.6 tok/s	Runs great	8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (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

8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 218 tok/s · Runs great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 (16 GB) F16 · 47.0 tok/s · Runs great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 (16 GB) F16 · 82.7 tok/s · Runs great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 279 tok/s · Runs great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 288 tok/s · Runs great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 403 tok/s · Runs great

Quick answers

How much memory does SmolLM2 360M Instruct need on the AMD Ryzen 7 8845HS / Ryzen 7 255 NAS 96GB?

At F16 it needs about 5.5 GB. The AMD Ryzen 7 8845HS / Ryzen 7 255 NAS 96GB has 48.0 GB usable.

How fast is SmolLM2 360M Instruct on the AMD Ryzen 7 8845HS / Ryzen 7 255 NAS 96GB?

About 79.6 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of SmolLM2 360M Instruct should I use on the AMD Ryzen 7 8845HS / Ryzen 7 255 NAS 96GB?

F16. 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.