K2 Horizon 7B on NVIDIA GeForce RTX 3080 10GB

Can the NVIDIA GeForce RTX 3080 10GB run K2 Horizon 7B?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q6_K it needs about 9.7 GB of 10.0 GB usable, with an estimated speed of 71.9 tok/s.

Best quant: Q6_K
Generation speed: 71.9 tok/s
Prompt processing: 2,384 tok/s
First token (1K prompt): 0.4 s
Largest safe context: 10K

Best app to run it on the NVIDIA GeForce RTX 3080 10GB

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open K2 Horizon 7B in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open K2 Horizon 7B in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

Want an agent? K2 Horizon 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 K2 Horizon 7B

Recommended for the NVIDIA GeForce RTX 3080 10GB: Q6_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q6_K file (opens in a new tab)

huggingface.co/IFM/K2-Horizon-7B-GGUF (opens in a new tab)

ollama run hf.co/IFM/K2-Horizon-7B-GGUF:Q6_K

Original weights · Hugging Face

Full-precision files from Institute of Foundation Models, for fine-tuning, vLLM, Transformers.

huggingface.co/IFM/K2-Horizon-7B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Institute of Foundation Models. The weights themselves download from Hugging Face.

github.com/ifm-ai/xllm (opens in a new tab)

IFM’s official training code (xLLM) for the K2 Horizon family.

git clone https://github.com/ifm-ai/xllm

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_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 welltight fit: How well it runs on the NVIDIA GeForce RTX 3080 10GB: 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.	35.6 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	24.0 / 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.	15.0 / 15
Match score	89.6 / 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 GeForce RTX 3080 10GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.9 GB	10.0 GB	170 tok/s	Runs great	56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	6.7 GB	10.0 GB	134 tok/s	Runs great	67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	7.8 GB	10.0 GB	104 tok/s	Runs great	76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	8.7 GB	10.0 GB	85.6 tok/s	Runs welltight fit	77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	9.7 GB	10.0 GB	71.9 tok/s	Runs welltight fit	79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	11.8 GB	10.0 GB	17.5 tok/s	Runs welloffloads to RAM	80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	20.3 GB	10.0 GB	3.5 tok/s	Slowheavy RAM offload	80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (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

80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 46.7 tok/s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 51.1 tok/s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 62.2 tok/s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 66.7 tok/s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 F16 · 57.3 tok/s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 38.3 tok/s · Runs great

Quick answers

How much memory does K2 Horizon 7B need on the RTX 3080 10GB?

At Q6_K it needs about 9.7 GB. The RTX 3080 10GB has 10.0 GB usable.

How fast is K2 Horizon 7B on the RTX 3080 10GB?

About 71.9 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of K2 Horizon 7B should I use on the RTX 3080 10GB?

Q6_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.