FitMyLLM
MBZUAI IFM/Dense

MK2 Horizon 3.7B

K2 Horizon 3.7B is the small dense member of MBZUAI IFM's fully open K2 Horizon family: 3.7B of transformer plus a large 250K-token vocabulary, about 5B on disk, with a 512K context.

chatcodingreasoningmathagentictool_use
5.06B
Parameters
512K
Context length
7
Benchmarks
6
Quantizations
18K
HF downloads
Architecture
Dense
Released
2026-09-03
Layers
36
KV Heads
8
Head Dim
128
Family
other

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
5.3 GB
3.6 + 1.7 KV
good
Q5_K_S5.57
5.7 GB
4.0 + 1.7 KV
good
Q5_K_M5.7
5.8 GB
4.1 + 1.7 KV
good
Q6_K6.56
6.3 GB
4.6 + 1.7 KV
excellent
Q8_08.5
7.6 GB
5.9 + 1.7 KV
lossless
FP1616
12.3 GB
10.6 + 1.7 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 3.7B 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 (7)

GPQA Diamond69.2
SWE-bench65.6
AA Long Context62.3
Terminal-Bench 2.128.1
SciCode22.0
HLE13.9
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:5b-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 Tesla C1080
4 GB VRAM • 102 GB/s
NVIDIA
NVIDIA Tesla K10
4 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M4
4 GB VRAM • 88 GB/s
NVIDIA
NVIDIA GeForce GTX 1050 Ti
4 GB VRAM • 112 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon Instinct MI8
4 GB VRAM • 512 GB/s
AMD
NVIDIA GeForce GTX 1650
4 GB VRAM • 128 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 1650 SUPER
4 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 5300 XT OEM
4 GB VRAM • 112 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 5500 OEM
4 GB VRAM • 224 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 5500 XT
4 GB VRAM • 224 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 5500M
4 GB VRAM • 224 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 1650 GDDR6
4 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 1650 TU106
4 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 1650 TU116
4 GB VRAM • 192 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce GTX 1630
4 GB VRAM • 96 GB/s
NVIDIA
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce RTX 3050 4 GB
4 GB VRAM • 192 GB/s
NVIDIA
$149
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA RTX A1000 Embedded
4 GB VRAM • 224 GB/s
NVIDIA
NVIDIA RTX A2000 Embedded
4 GB VRAM • 192 GB/s
NVIDIA
AMD Radeon RX 6400
4 GB VRAM • 128 GB/s
AMD
$139
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 6500 XT
4 GB VRAM • 144 GB/s
AMD
$70
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 6500M
4 GB VRAM • 144 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 6600S
4 GB VRAM • 224 GB/s
AMD
$175
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
Intel Arc A310
4 GB VRAM • 124 GB/s
INTEL
$79
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
Intel Arc A350
4 GB VRAM • 124 GB/s
INTEL
$99
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
Intel Arc A350M
4 GB VRAM • 112 GB/s
INTEL
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
Intel Arc A370M
4 GB VRAM • 112 GB/s
INTEL
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 6450M
4 GB VRAM • 128 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 6550M
4 GB VRAM • 144 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
AMD Radeon RX 6550S
4 GB VRAM • 128 GB/s
AMD
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai
NVIDIA GeForce RTX 4010
4 GB VRAM • 96 GB/s
NVIDIA
$199
AmazonNeweggeBayPCPartPickerRent on RunPodRent on Vast.ai

Find the best GPU for K2 Horizon 3.7B

Build Hardware for K2 Horizon 3.7B
▸ SPEC SHEET

K2 Horizon 3.7B — 5.06B Dense.

▸ SPECIFICATIONS
PARAMETERS
5.06B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
512K tokens
CAPABILITIES
chat, coding, reasoning, math, agentic, tool_use
RELEASE DATE
2026-09-03
PROVIDER
MBZUAI IFM
FAMILY
other
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.893.6 GB94%
Q5_K_S5.574.0 GB96%
Q5_K_M5.74.1 GB96%
Q6_K6.564.6 GB97%
Q8_08.55.9 GB100%
FP161610.6 GB100%
§ 01BENCHMARK SCORES
GPQA Diamond69.2
HLE13.9
aa_scicode22.0
aa_lcr62.3
SWE-bench65.6
aa_terminal_bench_v228.1
aa_terminal_bench_v40.0
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA Tesla C1080
4 GB · 102 GB/s
NVIDIA Tesla K10
4 GB · 160 GB/s
NVIDIA Tesla M4
4 GB · 88 GB/s
NVIDIA GeForce GTX 1050 Ti
4 GB · 112 GB/s
AMD Radeon Instinct MI8
4 GB · 512 GB/s
NVIDIA GeForce GTX 1650
4 GB · 128 GB/s
NVIDIA GeForce GTX 1650 SUPER
4 GB · 192 GB/s
AMD Radeon RX 5300 XT OEM
4 GB · 112 GB/s
AMD Radeon RX 5500 OEM
4 GB · 224 GB/s
AMD Radeon RX 5500 XT
4 GB · 224 GB/s
AMD Radeon RX 5500M
4 GB · 224 GB/s
NVIDIA GeForce GTX 1650 GDDR6
4 GB · 192 GB/s
NVIDIA GeForce GTX 1650 TU106
4 GB · 192 GB/s
NVIDIA GeForce GTX 1650 TU116
4 GB · 192 GB/s
NVIDIA GeForce GTX 1630
4 GB · 96 GB/s