CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / K2-Horizon-7B-oQ6e
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

K2-Horizon-7B-oQ6e

Date: 2026-11-15Commit: 2cca82eSigned: 2DC28CC7B26A283B ✓

Text generation model with 9B parameters. Safetensors weights, 7.56 GB in all. Published by mlx-community under Apache-2.0.

9B params7.56GBK2-Horizon-7B-oQ6esafetensorspermissive
FactsParams9BSize7.56 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/K2-Horizon-7B-oQ6e
# manifest sha256 3364f1266972… · 7.56 GB · 13 files
$ fw verify ./K2-Horizon-7B-oQ6e mlx-community/K2-Horizon-7B-oQ6e
From sourceHosted (signed)mlx-community/K2-Horizon-7B-oQ6eLast check: 2026-11-15 05:11 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of K2-Horizon-7B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
7.56 GB
Weights
7.54 GB (safetensors)
Parameters
9B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
13, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: IFM/K2-Horizon-7B

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:11 UTCpassed

Model card

From the publisher at commit 2cca82e. Shown as plain text with links; images open at the publisher.

K2-Horizon-7B oQ6e#

oQ6e (imatrix-enhanced mixed-precision 6-bit) conversion of IFM/K2-Horizon-7B, a dense reasoning model from the K2 Horizon family (7B parameters, 512K context).

Upstream model: IFM/K2-Horizon-7B by the IFM Team, released under Apache-2.0.

Conversion: Quantized to MLX format using Hermes Agent with mlx-lm and oMLX.

Quickstart#

pip install -U mlx-lm

python3 -m mlx_lm.generate   --model hermitdave/K2-Horizon-7B-oQ6e   --prompt "Explain why long-context evaluation is difficult."   --max-tokens 512 --temp 1.0 --top-p 0.95

Reasoning#

K2-Horizon is a reasoning model. Always use reasoning_effort="high" for best results:

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="hermitdave/K2-Horizon-7B-oQ6e",
    messages=[{"role": "user", "content": "Explain quantum entanglement."}],
    extra_body={"chat_template_kwargs": {"reasoning_effort": "high"}},
)
print("Reasoning:", getattr(response.choices[0].message, "reasoning_content", None))
print("Answer:", response.choices[0].message.content)

Benchmark Results#

BenchmarkK2-Horizon-7B
SWE-bench Verified70.6
Terminal-Bench 2.139.06
tau3-Banking25.8
BrowseComp59.0
HMMT Feb 202673.3

Scores in %. See model card for full results.

oMLX Patch#

K2-Horizon requires oMLX v0.6.4+ with the K2-Horizon support patch (PR #3441). This patch adds:

  • k2_horizon model type support
  • Reasoning content handling (<ifm|think> tags)
  • Tool call parsing (plain text and XML formats)
  • Multi-turn conversation support

Without this patch, oMLX will refuse to load K2-Horizon models with ValueError: Model type k2_horizon not supported.

Chat Template#

K2-Horizon uses IFM's custom chat template with reasoning and tool calling support. Key tags:

TagPurpose
`<ifm\think>,<ifm\think_fast>,<ifm\think_faster>`Thinking blocks
`<\ifm\im_start>,<\ifm\im_end\>`Message delimiters
`<ifm\tool_call>,<ifm\arg_key>,<ifm\arg_value>`Tool call structure

All tags are automatically stripped by oMLX before responses reach users.

Citation#

@misc{k2horizon2026,
  title  = {Introducing K2 Horizon: Frontier Performance, Radically Open},
  author = {{IFM Team}},
  year   = {2026},
  url    = {https://ifm.ai/blog/k2/},
}

License#

Apache-2.0 (same as upstream).

Files

13 files · 7.56 GBWeights 7.54 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 13 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.89 KB61a0e4be7ba709cbf1bb77aec44cffe9307610cb75ea3dc00af13a6a2a75e690
chat_template.jinja51.0 KBa892cd0b0195599f283a8c706787520d9a6747640efb2f4dec4144b0abb62590
config.json9.26 KB3d4767551c5c8e0d753dcbc9cd1ac018145f850db5817701e7c1684ef45690dc
configuration_k2_horizon.py3.53 KB5c2f993c1053d9462ebea6dea416c897fddfbb4a5edd904e486936b20d4badc5
generation_config.json81 B2da7d47641f4509da4ae47711e31d8b5f0f3f801ee08d87e7e9f07f814bdc4a3
model-00001-of-00002.safetensors5.03 GBdb6a7544325175bad3446291b88078f7fbb54a9a273cc5cfffed68c960d92c78
model-00002-of-00002.safetensors2.51 GBd8d0a96443e47448f2421b5aea498f2081bdf002b9acddcd97c027e7e2dc8f85
model.safetensors.index.json68.1 KBf5949be9fed64f17f9b6569836638c10087fd2e2f952bea00d4f9641075eaf71
modeling_k2_horizon.py49.5 KBfb09e010956bd51cfa7d4055b4381cff34c9e06164066b49e3546f38b2e6242f
oq_imatrix_report.json12.7 KB7c3469b21a78401e81528e463601b6571b406d151dcf5fefb8a349b18921e13d
tokenizer.json20.6 MB838d767b7c9925ff257feb20eaa4299a8e3cc35bb3d805589c373f51d2cc3cb6
tokenizer_config.json293 B068cfdcf2bcef44fd77f935a9fb41b4d45af547fd41b95079817bd40b24fe518
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
2cca82ec88 pinned now2026-11-15 05:11 UTC13 files · 7.56 GB

Use it

$ fw get mlx-community/K2-Horizon-7B-oQ6e
# manifest sha256 3364f1266972… · 7.56 GB · 13 files
$ fw verify ./K2-Horizon-7B-oQ6e mlx-community/K2-Horizon-7B-oQ6e
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/K2-Horizon-7B-oQ6e.json --dir ./K2-Horizon-7B-oQ6e $ python3 fw.py verify ./K2-Horizon-7B-oQ6e ./mlx-community__K2-Horizon-7B-oQ6e.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/K2-Horizon-7B-oQ6e --revision 2cca82ec88e24bd5fc264e4bcd29922182c8f62f --local-dir ./K2-Horizon-7B-oQ6e
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("mlx-community/K2-Horizon-7B-oQ6e", revision="2cca82ec88e24bd5fc264e4bcd29922182c8f62f") model = AutoModelForCausalLM.from_pretrained("mlx-community/K2-Horizon-7B-oQ6e", revision="2cca82ec88e24bd5fc264e4bcd29922182c8f62f", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/K2-Horizon-7B-oQ6e --revision 2cca82ec88e24bd5fc264e4bcd29922182c8f62f
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
61a0e4be7ba709cbf1bb77aec44cffe9307610cb75ea3dc00af13a6a2a75e690
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject: K2-Horizon-7B-oQ6eDate: 2026-11-15Commit: 2cca82eSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/K2-Horizon-7B-oQ6e
Pinned commit
2cca82ec88e24bd5fc264e4bcd29922182c8f62f
Manifest
K2-Horizon-7B-oQ6e.json · .minisig
Manifest sha256
3364f12669729be87977843b8ba9630f73863157c20bd1e751b61aaf3632b931
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:11 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/K2-Horizon-7B-oQ6e.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/K2-Horizon-7B-oQ6e.json.minisig $ minisign -Vm K2-Horizon-7B-oQ6e.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

IFM/K2-Horizon-7B · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/K2-Horizon-7B-oQ6e
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. K2-Horizon-7B-oQ6e.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/K2-Horizon-7B-oQ6e

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B