Text / IFM

K2 Horizon 7B

K2-Horizon 7B is a 7B-core dense, decoder-only text-generation model from the K2-Horizon family, available under the apache-2.0 license with safetensors format and transformers library support. It has a 512K (524,288-token) native context window from midtraining onward, supports English, and was trained on IFM/K2-Horizon-Pretrain-Data and IFM/K2-Horizon-Midtrain-Data. The model card highlights strong dense-baseline performance across agentic, coding, long-context, and reasoning benchmarks according to the supplied chart/table, diffusion adapters referenced on Hugging Face for faster inference, released intermediate checkpoints, and public training data, recipe, code, and evaluation resources.

EstimatedRepository opened Sep 1, 2026Source checked 9/23/2026Version: 446bf311

LOCALRENTED GPUOPEN WEIGHTS

Freshness 84 out of 100. Repository age: 44 days old, Sep 1, 2026. Measures age, not quality.

Popularity 66 out of 100. 81,808 downloads in 30 days; 254 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters: 9.00B
Architecture: k2_horizon
Context length: 524,288
License: apache-2.0
Disk space: 16.8 GB
Software: SGLang, vLLM, Transformers

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

Text generation in English with the transformers library.
Long-context tasks up to the stated 512K context window.
Agentic benchmark-style tasks as evaluated in the supplied model card.
Coding benchmark-style tasks as evaluated in the supplied model card.
Reasoning benchmark-style tasks as evaluated in the supplied model card.

Tradeoffs

Only English language support is listed.
Context length is limited to the stated 512K-token window.
Benchmark results are reported only for the specific chart and table shown; no independent testing is claimed.
Diffusion adapters are referenced externally and are not part of this model's provided files.
No detailed hardware, quantization, or deployment compatibility requirements are provided in the source data.

Ways to run it

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

sglang serve  --model-path IFM/K2-Horizon-7B  --revision 30d38fecf8a609873ae73a617f5c714286e1f565  --tp 1  --dtype bfloat16  --attention-backend fa3  --reasoning-parser k2_horizon  --host 0.0.0.0  --port 30000

Official instructions

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve IFM/K2-Horizon-7B  --trust-remote-code  --dtype bfloat16  --tensor-parallel-size 1  --reasoning-parser k2_horizon  --enable-auto-tool-choice  --tool-call-parser k2_horizon

Official instructions

Transformers · See official guide

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "IFM/K2-Horizon-7B"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, device_map="auto", dtype="bfloat16", low_cpu_mem_usage=True, trust_remote_code=True
)

inputs = tokenizer("Explain why long-context evaluation is difficult.", return_tensors="pt").to(model.device)
inputs.pop("token_type_ids", None)
outputs = model.generate(**inputs, max_new_tokens=32768, temperature=1.0, top_p=0.95, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text

Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.

MODEL SIZE27.36B

LOCALRENTED GPU

Released Sep 17, 2026

Text

DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.

Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3

LOCALRENTED GPU

Repository opened Sep 10, 2026

Text

Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats

LOCALRENTED GPU

Compare versions →