FITMYLLM·AUGUST 17, 2026·OPEN METHODOLOGY · COMMUNITY BENCHMARKS

LIVE·UPDATED DAILY

Independent benchmarks for self-hosted AI infrastructure.

▸Privacy Shield

Upstage/Dense

USOLAR-Pro 22B

Upstage SOLAR Pro 22B — depth-upscaled model with strong reasoning and instruction following.

chatreasoningThinking

22.1B

Parameters

4K

Context length

7

Benchmarks

10

Quantizations

30K

HF downloads

Architecture

Dense

Released

2024-10-15

Layers

64

KV Heads

10

Head Dim

128

Family

solar

Quantization Options

Quant	Bits	VRAM @ 4K	Quality
Q3_K_M	4	11.5 GB	low
Q3_K_L	4.3	12.4 GB	moderate
IQ4_XS	4.46	12.8 GB	moderate
Q4_K_S	4.67	13.4 GB	moderate
Q4_K_M	4.89	14.0 GB	good
Q5_K_S	5.57	15.9 GB	good
Q5_K_M	5.7	16.2 GB	good
Q6_K	6.56	18.6 GB	excellent
Q8_0	8.5	24.0 GB	lossless
FP16	16	44.7 GB	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 SOLAR-PRO 22B 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)

IFEval73.0

BBH69.0

HumanEval66.0

MMLU-PRO48.0

MATH22.1

GPQA16.1

MUSR15.0

Run this model

▸Easiest way to get started·Beginners

curl -fsSL https://ollama.com/install.sh | sh

$ollama run solar-pro:22b-preview-instruct-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ 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

HuggingFace Ollama Library GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 5080

16 GB VRAM • 960 GB/s

NVIDIA

$999

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 5070 Ti

16 GB VRAM • 896 GB/s

NVIDIA

$749

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4080 SUPER

16 GB VRAM • 736 GB/s

NVIDIA

$999

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4080

16 GB VRAM • 717 GB/s

NVIDIA

$1199

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4070 Ti SUPER

16 GB VRAM • 672 GB/s

NVIDIA

$799

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX 4060 Ti 16GB

16 GB VRAM • 288 GB/s

NVIDIA

$499

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD RX 7900 GRE

16 GB VRAM • 576 GB/s

AMD

$549

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

16 GB VRAM • 624 GB/s

AMD

$499

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

16 GB VRAM • 288 GB/s

AMD

$329

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

16 GB VRAM • 576 GB/s

AMD

$449

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

16 GB VRAM • 512 GB/s

AMD

$469

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

16 GB VRAM • 512 GB/s

AMD

$599

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

16 GB VRAM • 512 GB/s

AMD

$599

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Intel Arc A770 16GB

16 GB VRAM • 560 GB/s

INTEL

$349

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Apple M1 Pro (16GB)

16 GB VRAM • 200 GB/s

APPLE

$999

Apple M2 Pro (16GB)

16 GB VRAM • 200 GB/s

APPLE

$1299

Apple M4 (16GB)

16 GB VRAM • 120 GB/s

APPLE

$499

NVIDIA Tesla T4 16GB

16 GB VRAM • 320 GB/s

NVIDIA

$800

NVIDIA V100 PCIe 16GB

16 GB VRAM • 900 GB/s

NVIDIA

$2000

16 GB VRAM • 640 GB/s

AMD

$599

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

16 GB VRAM • 672 GB/s

AMD

$549

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Apple M1 (16GB)

16 GB VRAM • 68.25 GB/s

APPLE

$699

Apple M2 (16GB)

16 GB VRAM • 100 GB/s

APPLE

$799

Apple M3 (16GB)

16 GB VRAM • 100 GB/s

APPLE

$799

NVIDIA RTX 5060 Ti 16GB

16 GB VRAM • 448 GB/s

NVIDIA

$429

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA Tesla P100 DGXS

16 GB VRAM • 732 GB/s

NVIDIA

NVIDIA Tesla P100 PCIe 16 GB

16 GB VRAM • 732 GB/s

NVIDIA

NVIDIA Tesla P100 SXM2

16 GB VRAM • 732 GB/s

NVIDIA

NVIDIA Tesla V100 PCIe 16 GB

16 GB VRAM • 897 GB/s

NVIDIA

NVIDIA Tesla V100 SXM2 16 GB

16 GB VRAM • 1130 GB/s

NVIDIA

Find the best GPU for SOLAR-Pro 22B

Build Hardware for SOLAR-Pro 22B

Model Card

View on HuggingFace

Upstage SOLAR Pro 22B — depth-upscaled model with strong reasoning and instruction following.

▸ SPEC SHEET

SOLAR-Pro 22B — 22.1B Dense.

▸ SPECIFICATIONS

PARAMETERS: 22.1B
ARCHITECTURE: Dense Transformer
CONTEXT LENGTH: 4K tokens
CAPABILITIES: chat, reasoning
RELEASE DATE: 2024-10-15
PROVIDER: Upstage
FAMILY: solar

▸ VRAM REQUIREMENTS

QUANT	BPW	VRAM	QUALITY
Q3_K_M	4	11.5 GB	88%
Q3_K_L	4.3	12.4 GB	90%
IQ4_XS	4.46	12.8 GB	92%
Q4_K_S	4.67	13.4 GB	93%
Q4_K_M	4.89	14.0 GB	94%
Q5_K_S	5.57	15.9 GB	96%
Q5_K_M	5.7	16.2 GB	96%
Q6_K	6.56	18.6 GB	97%
Q8_0	8.5	24.0 GB	100%
FP16	16	44.7 GB	100%

§ 01BENCHMARK SCORES

HumanEval66.0

MMLU-PRO48.0

MATH22.1

IFEval73.0

BBH69.0

GPQA16.1

MUSR15.0

§ 02RUN COMMAND

Run SOLAR-Pro 22B locally with Ollama — needs 14.0 GB VRAM at Q4_K_M:

$ollama run solar-pro:22b

§ 03COMPATIBLE GPUs

30 @ Q4_K_M

NVIDIA RTX 5080

16 GB · 960 GB/s

NVIDIA RTX 5070 Ti

16 GB · 896 GB/s

NVIDIA RTX 4080 SUPER

16 GB · 736 GB/s

NVIDIA RTX 4080

16 GB · 717 GB/s

NVIDIA RTX 4070 Ti SUPER

16 GB · 672 GB/s

NVIDIA RTX 4060 Ti 16GB

16 GB · 288 GB/s

AMD RX 7900 GRE

16 GB · 576 GB/s

16 GB · 624 GB/s

16 GB · 288 GB/s

16 GB · 576 GB/s

16 GB · 512 GB/s

16 GB · 512 GB/s

16 GB · 512 GB/s

Intel Arc A770 16GB

16 GB · 560 GB/s

Apple M1 Pro (16GB)

16 GB · 200 GB/s