Qwen2.5 Coder 32B Instruct on Intel Arc A770 16GB

Can the Intel Arc A770 16GB run Qwen2.5 Coder 32B Instruct?

Yes, it runs well (offloads to RAM)

Runs well (offloads to RAM). At Q2_K it needs about 16.7 GB of 16.0 GB usable, with an estimated speed of 20.6 tok/s.

Best quant: Q2_K
Generation speed: 20.6 tok/s
Prompt processing: 636 tok/s
First token (1K prompt): 1.6 s
Largest safe context: 5K

Best app to run it on the Intel Arc A770 16GB

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 Qwen/Qwen2.5-Coder-32B-Instruct-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 Qwen/Qwen2.5-Coder-32B-Instruct-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? Qwen2.5 Coder 32B 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 Qwen2.5 Coder 32B Instruct

Recommended for the Intel Arc A770 16GB: 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 qwen2.5-coder:32b-instruct-q2_K

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/Qwen/Qwen2.5-Coder-32B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/QwenLM/Qwen3-Coder (opens in a new tab)

Qwen’s coder repo, renamed from Qwen2.5-Coder to Qwen3-Coder.

git clone https://github.com/QwenLM/Qwen3-Coder

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (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 A770 16GB: 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.	21.1 / 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.	10.8 / 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	56.9 / 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 A770 16GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	16.7 GB	16.0 GB	20.6 tok/s	Runs welloffloads to RAM	46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	19.6 GB	16.0 GB	9.3 tok/s	Slowoffloads to RAM	56Good quality (B) · 56 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	23.6 GB	16.0 GB	5.3 tok/s	Slowheavy RAM offload	63Good quality (B) · 63 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`	26.8 GB	16.0 GB	3.8 tok/s	Slowheavy RAM offload	64Good quality (B) · 64 of 100: how capable the model is at Q5_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)
`Q6_K`	30.4 GB	16.0 GB	2.8 tok/s	Very slowheavy RAM offload	66Good quality (B) · 66 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	38.3 GB	16.0 GB	—	Won't run	67Good quality (B) · 67 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	69.1 GB	16.0 GB	—	Won't run	67Good quality (B) · 67 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 9 (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

66Good quality (B) · 66 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 46.5 tok/s · Runs well (tight fit)
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 37.7 tok/s · Runs well (tight fit)
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 35.0 tok/s · Runs well (tight fit)
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 30.9 tok/s · Runs well (tight fit)
66Good quality (B) · 66 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 46.5 tok/s · Runs great
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 17.6 tok/s · Runs well

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.