Granite Code 3B Instruct (128K) on Intel Arc Pro B70

Can the Intel Arc Pro B70 run Granite Code 3B Instruct (128K)?

Yes, it runs great

Runs great. At Q8_0 it needs about 8.6 GB of 32.0 GB usable, with an estimated speed of 83.4 tok/s.

Best quant: Q8_0
Generation speed: 83.4 tok/s
Prompt processing: 5,911 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 77K

Best app to run it on the Intel Arc Pro B70

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 mradermacher/granite-3b-code-instruct-128k-i1-GGUF:Q8_0

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 mradermacher/granite-3b-code-instruct-128k-i1-GGUF:Q8_0

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

Want an agent? Granite Code 3B Instruct (128K) 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 Granite Code 3B Instruct (128K)

Recommended for the Intel Arc Pro B70: Q8_0. 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 granite-code:3b-instruct-128k-q8_0

Quantized files · GGUF

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

huggingface.co/mradermacher/granite-3b-code-instruct-128k-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/granite-3b-code-instruct-128k-i1-GGUF

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-3b-code-instruct-128k (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 Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, 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 Intel Arc Pro B70: 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.	9.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	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.	6.2 / 15
Match score	55.2 / 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 Intel Arc Pro B70

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	6.3 GB	32.0 GB	269 tok/s	Runs great	14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	6.6 GB	32.0 GB	212 tok/s	Runs great	16Basic quality (D) · 16 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`	7.0 GB	32.0 GB	164 tok/s	Runs great	19Basic quality (D) · 19 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`	7.4 GB	32.0 GB	135 tok/s	Runs great	19Basic quality (D) · 19 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`	7.7 GB	32.0 GB	114 tok/s	Runs great	19Basic quality (D) · 19 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`	8.6 GB	32.0 GB	83.4 tok/s	Runs great	20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.
`F16`	11.8 GB	32.0 GB	38.4 tok/s	Runs great	20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (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

20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 45.6 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 55.6 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 60.9 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti F16 · 74.2 tok/s · Runs great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 F16 · 79.4 tok/s · Runs great
19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q6_K · 66.6 tok/s · Runs great

Quick answers

How much memory does Granite Code 3B Instruct (128K) need on the Arc Pro B70 32GB?

At Q8_0 it needs about 8.6 GB. The Arc Pro B70 32GB has 32.0 GB usable.

How fast is Granite Code 3B Instruct (128K) on the Arc Pro B70 32GB?

About 83.4 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Granite Code 3B Instruct (128K) should I use on the Arc Pro B70 32GB?

Q8_0. 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.