FitMyLLM
MBZUAI IFM/Dense

MK2 Horizon 0.9B

K2 Horizon 0.9B is the smallest of MBZUAI IFM's fully open K2 Horizon models, distilled from domain teachers for maths, code and STEM, with a 128K context. Small enough for a phone.

chatcodingreasoningmath
1.08B
Parameters
128K
Context length
8
Benchmarks
6
Quantizations
12K
HF downloads
Architecture
Dense
Released
2026-09-03
Layers
28
KV Heads
8
Head Dim
64
Family
other

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
1.8 GB
1.1 + 0.7 KV
good
Q5_K_S5.57
1.9 GB
1.2 + 0.7 KV
good
Q5_K_M5.7
1.9 GB
1.3 + 0.7 KV
good
Q6_K6.56
2.0 GB
1.4 + 0.7 KV
excellent
Q8_08.5
2.3 GB
1.6 + 0.7 KV
lossless
FP1616
3.3 GB
2.6 + 0.7 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN K2 HORIZON 0.9B NOW

Rent on Vast.ai →Or RunPod →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (8)

AIME41.7
LiveCodeBench37.4
GPQA Diamond29.3
SciCode6.9
AA Long Context6.3
HLE5.4
Terminal-Bench 2.11.1
Terminal-Bench 40.0

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run other:1b-q4_K_M

Tag may need adjustment — check ollama.com/library/other for available tags.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines
HuggingFaceGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA GeForce GTX 470
1 GB VRAM • 133.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 570
1 GB VRAM • 152 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 570 Rev. 2
1 GB VRAM • 152 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 460 v2 ES
1 GB VRAM • 128.3 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 560 OEM
1 GB VRAM • 128.3 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 560 Ti 448
1 GB VRAM • 152 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Quadro FX 5600
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Quadro FX 5600 Mac Edition
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Tesla C870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla D870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Tesla S870
2 GB VRAM • 76.8 GB/s
NVIDIA
NVIDIA Quadro CX
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Quadro FX 4800
2 GB VRAM • 76.8 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GT 230 OEM
2 GB VRAM • 24 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GT 440 OEM
2 GB VRAM • 43.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 460M
2 GB VRAM • 60 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 470M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 480
2 GB VRAM • 177.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 580
2 GB VRAM • 192.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GT 545
2 GB VRAM • 38.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 560M
2 GB VRAM • 60 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 570M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 580 Rev. 2
2 GB VRAM • 192.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 590
2 GB VRAM • 164 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GT 640 OEM Rebrand
2 GB VRAM • 38.4 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 670M
2 GB VRAM • 72 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 760 OEM Rebrand
2 GB VRAM • 179.2 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 260 OEM
2 GB VRAM • 112.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA Quadro 4000 Mac Edition
2 GB VRAM • 89.9 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD FireGL V8650
2 GB VRAM • 111 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai

Find the best GPU for K2 Horizon 0.9B

Build Hardware for K2 Horizon 0.9B
▸ SPEC SHEET

K2 Horizon 0.9B — 1.08B Dense.

▸ SPECIFICATIONS
PARAMETERS
1.08B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
128K tokens
CAPABILITIES
chat, coding, reasoning, math
RELEASE DATE
2026-09-03
PROVIDER
MBZUAI IFM
FAMILY
other
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.891.1 GB94%
Q5_K_S5.571.2 GB96%
Q5_K_M5.71.3 GB96%
Q6_K6.561.4 GB97%
Q8_08.51.6 GB100%
FP16162.6 GB100%
§ 01BENCHMARK SCORES
GPQA Diamond29.3
LiveCodeBench37.4
AIME41.7
HLE5.4
aa_scicode6.9
aa_lcr6.3
aa_terminal_bench_v21.1
aa_terminal_bench_v40.0
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA GeForce GTX 470
1 GB · 133.9 GB/s
NVIDIA GeForce GTX 570
1 GB · 152 GB/s
NVIDIA GeForce GTX 570 Rev. 2
1 GB · 152 GB/s
NVIDIA GeForce GTX 460 v2 ES
1 GB · 128.3 GB/s
NVIDIA GeForce GTX 560 OEM
1 GB · 128.3 GB/s
NVIDIA GeForce GTX 560 Ti 448
1 GB · 152 GB/s
NVIDIA Quadro FX 5600
2 GB · 76.8 GB/s
NVIDIA Quadro FX 5600 Mac Edition
2 GB · 76.8 GB/s
NVIDIA Tesla C870
2 GB · 76.8 GB/s
NVIDIA Tesla D870
2 GB · 76.8 GB/s
NVIDIA Tesla S870
2 GB · 76.8 GB/s
NVIDIA Quadro CX
2 GB · 76.8 GB/s
NVIDIA Quadro FX 4800
2 GB · 76.8 GB/s
NVIDIA GeForce GT 230 OEM
2 GB · 24 GB/s
NVIDIA GeForce GT 440 OEM
2 GB · 43.2 GB/s