on

Can the Intel Arc B580 run Granite Code 34B Instruct?

28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well (offloads to RAM)

Runs well (offloads to RAM). At Q2_K it needs about 15.1 GB of 12.0 GB usable, with an estimated speed of 10.6 tok/s.

Best quant
Q2_K
Generation speed
10.6 tok/s
Prompt processing
375 tok/s
First token (1K prompt)
2.7 s
Largest safe context
—

Best app to run it on the Intel Arc B580

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

  • Splits the model between GPU memory and system RAM, which this setup needs.
  • Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
  • Supports Intel Arc through SYCL and Vulkan.
llama-server -hf ibm-granite/granite-34b-code-instruct-8k-GGUF:Q2_K
  • LM Studio 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

llama.cpp

Command line + local API · runs on llama.cpp

  • Splits the model between GPU memory and system RAM, which this setup needs.
  • Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
  • Supports Intel Arc through SYCL and Vulkan.
llama-server -hf ibm-granite/granite-34b-code-instruct-8k-GGUF:Q2_K
  • LM Studio 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.

Want an agent? Granite Code 34B Instruct 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 34B Instruct

Recommended for the Intel Arc B580: 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 granite-code:34b-instruct-q2_K

Quantized files · GGUF

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

huggingface.co/ibm-granite/granite-34b-code-instruct-8k-GGUF (opens in a new tab)

ollama run hf.co/ibm-granite/granite-34b-code-instruct-8k-GGUF

Original weights · Hugging Face

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

huggingface.co/ibm-granite/granite-34b-code-instruct-8k (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 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (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 Runs welloffloads to RAM
How well it runs on the Intel Arc B580: 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.12.6 / 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.7.7 / 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 score45.3 / 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 B580

Quant Memory needed Available Speed Runs Quality Download
Q2_K 15.1 GB 12.0 GB 10.6 tok/s Runs welloffloads to RAM 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.
Q3_K_M 18.1 GB 12.0 GB 6.4 tok/s Slowheavy RAM offload 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.
Q4_K_M 22.1 GB 12.0 GB 4.1 tok/s Slowheavy RAM offload 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 25.5 GB 12.0 GB 3.1 tok/s Slowheavy RAM offload 38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.
Q6_K 29.2 GB 12.0 GB 2.4 tok/s Very slowheavy RAM offload 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.
Q8_0 37.3 GB 12.0 GB — Won't run 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.
F16 69.0 GB 12.0 GB — Won't run 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 5/100 (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

Quick answers

How much memory does Granite Code 34B Instruct need on the Arc B580 12GB?

At Q2_K it needs about 15.1 GB. The Arc B580 12GB has 12.0 GB usable.

How fast is Granite Code 34B Instruct on the Arc B580 12GB?

About 10.6 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Granite Code 34B Instruct should I use on the Arc B580 12GB?

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.

Was this page helpful?