StarCoder2 7B on LattePanda Sigma (32 GB)

Can the LattePanda Sigma (32 GB) run StarCoder2 7B?

Yes, it runs well

Runs well. At Q3_K_M it needs about 5.9 GB of 16.0 GB usable, with an estimated speed of 17.3 tok/s.

Best quant: Q3_K_M
Generation speed: 17.3 tok/s
Prompt processing: 284 tok/s
First token (1K prompt): 3.6 s
Largest safe context: 16K

Best app to run it on the LattePanda Sigma (32 GB)

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf QuantFactory/starcoder2-7b-GGUF:Q3_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama Intel GPU support here is experimental (Vulkan).

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf QuantFactory/starcoder2-7b-GGUF:Q3_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama Intel GPU support here is experimental (Vulkan).

Want an agent? StarCoder2 7B 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, 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 StarCoder2 7B

Recommended for the LattePanda Sigma (32 GB): Q3_K_M. 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 starcoder2:7b-q3_K_M

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/QuantFactory/starcoder2-7b-GGUF (opens in a new tab)

ollama run hf.co/QuantFactory/starcoder2-7b-GGUF:Q3_K_M

Original weights · Hugging Face

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

huggingface.co/bigcode/starcoder2-7b (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (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 well: How well it runs on the LattePanda Sigma (32 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.	9.1 / 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.	9.9 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	8.6 / 15
Match score	52.5 / 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 LattePanda Sigma (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.3 GB	16.0 GB	22.0 tok/s	Runs well	16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	5.9 GB	16.0 GB	17.3 tok/s	Runs well	20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	6.8 GB	16.0 GB	13.4 tok/s	Runs well	22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	7.5 GB	16.0 GB	11.1 tok/s	Runs well	23Basic quality (D) · 23 of 100: how capable the model is at Q5_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)
`Q6_K`	8.3 GB	16.0 GB	9.3 tok/s	Slow	23Basic quality (D) · 23 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	10.0 GB	16.0 GB	6.8 tok/s	Slow	24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	16.8 GB	16.0 GB	2.7 tok/s	Very slowover GPU memory limit	24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 39/100 (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

24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 43.9 tok/s · Runs great
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 F16 · 40.5 tok/s · Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q6_K · 41.4 tok/s · Runs great
23Basic quality (D) · 23 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q6_K · 42.8 tok/s · Runs great
22Basic quality (D) · 22 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. NVIDIA GeForce RTX 4060 Q4_K_M · 46.6 tok/s · Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 48.0 tok/s · Runs great

Quick answers

How much memory does StarCoder2 7B need on the LattePanda Sigma 32GB?

At Q3_K_M it needs about 5.9 GB. The LattePanda Sigma 32GB has 16.0 GB usable.

How fast is StarCoder2 7B on the LattePanda Sigma 32GB?

About 17.3 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of StarCoder2 7B should I use on the LattePanda Sigma 32GB?

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.