Qwen2.5 Coder 14B Instruct on NVIDIA GB10 (128 GB)

Can the NVIDIA GB10 (128 GB) run Qwen2.5 Coder 14B Instruct?

Yes, it runs well

Runs well. At Q4_K_M it needs about 20.4 GB of 115 GB usable, with an estimated speed of 22.7 tok/s.

Best quant: Q4_K_M
Generation speed: 22.7 tok/s
Prompt processing: 1,511 tok/s
First token (1K prompt): 0.7 s
Largest safe context: 32K

Best app to run it on the NVIDIA GB10 (128 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 qwen2.5-coder:14b-instruct-q4_K_M

vLLM The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
LM Studio Point-and-click: search, download and chat in one window.

Want an agent? Qwen2.5 Coder 14B 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 14B Instruct

Recommended for the NVIDIA GB10 (128 GB): Q4_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 qwen2.5-coder:14b-instruct-q4_K_M

Quantized files · GGUF

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

Download the Q4_K_M file (opens in a new tab)

huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen2.5-Coder-14B-Instruct-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen2.5-Coder-14B-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 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_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 NVIDIA GB10 (128 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.	28.2 / 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.	11.3 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	4.1 / 15
Match score	68.6 / 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 NVIDIA GB10 (128 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	17.3 GB	115 GB	37.3 tok/s	Runs great	46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	18.7 GB	115 GB	29.3 tok/s	Runs well	55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	20.4 GB	115 GB	22.7 tok/s	Runs well	62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	21.9 GB	115 GB	18.7 tok/s	Runs well	64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	23.5 GB	115 GB	15.7 tok/s	Runs well	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	27.1 GB	115 GB	11.6 tok/s	Runs well	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	41.0 GB	115 GB	5.3 tok/s	Slow	66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (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 Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 42.6 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 39.6 tok/s · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 47.7 tok/s · Runs great
64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q5_K_M · 46.1 tok/s · Runs great
64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q5_K_M · 50.5 tok/s · Runs great
64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q5_K_M · 61.5 tok/s · Runs great

Quick answers

How much memory does Qwen2.5 Coder 14B Instruct need on the NVIDIA GB10 128GB?

At Q4_K_M it needs about 20.4 GB. The NVIDIA GB10 128GB has 115 GB usable.

How fast is Qwen2.5 Coder 14B Instruct on the NVIDIA GB10 128GB?

About 22.7 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen2.5 Coder 14B Instruct should I use on the NVIDIA GB10 128GB?

Q4_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.