FitMyLLM
Upstage/Dense

USOLAR-10.7B

We introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks.

chat
10.7B
Parameters
4K
Context length
8
Benchmarks
10
Quantizations
27K
HF downloads
Architecture
Dense
Released
2023-12-13
Layers
48
KV Heads
8
Head Dim
128
Family
solar

Quantization Options

QuantBitsVRAM @ 4KQuality
Q3_K_M4
5.8 GB
low
Q3_K_L4.3
6.2 GB
moderate
IQ4_XS4.46
6.5 GB
moderate
Q4_K_S4.67
6.7 GB
moderate
Q4_K_M4.89
7.0 GB
good
Q5_K_S5.57
7.9 GB
good
Q5_K_M5.7
8.1 GB
good
Q6_K6.56
9.3 GB
excellent
Q8_08.5
11.9 GB
lossless
FP1616
21.9 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-10.7B 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 (8)

IFEval65.0
HumanEval37.2
MBPP36.2
BBH28.5
MMLU-PRO28.3
MATH12.2
MUSR11.7
GPQA6.5

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run solar:10.7b-text-v1-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
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 4060 Ti 8GB
8 GB VRAM • 288 GB/s
NVIDIA
$399
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 4060
8 GB VRAM • 272 GB/s
NVIDIA
$299
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3070 Ti
8 GB VRAM • 608 GB/s
NVIDIA
$499
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3070
8 GB VRAM • 448 GB/s
NVIDIA
$325
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3060 Ti
8 GB VRAM • 448 GB/s
NVIDIA
$250
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3050 8GB
8 GB VRAM • 224 GB/s
NVIDIA
$249
AmazonNeweggeBayPCPartPicker
AMD RX 7600
8 GB VRAM • 288 GB/s
AMD
$269
AmazonNeweggeBayPCPartPicker
AMD RX 6650 XT
8 GB VRAM • 280 GB/s
AMD
$399
AmazonNeweggeBayPCPartPicker
Intel Arc A750
8 GB VRAM • 512 GB/s
INTEL
$199
AmazonNeweggeBayPCPartPicker
Apple M1 (8GB)
8 GB VRAM • 68 GB/s
APPLE
$499
Apple M2 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
Apple M3 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
NVIDIA RTX 2080 SUPER
8 GB VRAM • 496 GB/s
NVIDIA
$280
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 2080
8 GB VRAM • 448 GB/s
NVIDIA
$260
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 2070 SUPER
8 GB VRAM • 448 GB/s
NVIDIA
$240
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 2070
8 GB VRAM • 448 GB/s
NVIDIA
$200
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 2060 SUPER
8 GB VRAM • 448 GB/s
NVIDIA
$180
AmazonNeweggeBayPCPartPicker
NVIDIA GTX 1080
8 GB VRAM • 320 GB/s
NVIDIA
$130
AmazonNeweggeBayPCPartPicker
NVIDIA GTX 1070 Ti
8 GB VRAM • 256 GB/s
NVIDIA
$120
AmazonNeweggeBayPCPartPicker
NVIDIA GTX 1070
8 GB VRAM • 256 GB/s
NVIDIA
$100
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 3060 8GB
8 GB VRAM • 224 GB/s
NVIDIA
$280
AmazonNeweggeBayPCPartPicker
AMD RX 6600 XT
8 GB VRAM • 256 GB/s
AMD
$200
AmazonNeweggeBayPCPartPicker
AMD RX 6600
8 GB VRAM • 224 GB/s
AMD
$165
AmazonNeweggeBayPCPartPicker
AMD RX 5700 XT
8 GB VRAM • 448 GB/s
AMD
$150
AmazonNeweggeBayPCPartPicker
AMD RX 5700
8 GB VRAM • 448 GB/s
AMD
$130
AmazonNeweggeBayPCPartPicker
Intel Arc A580
8 GB VRAM • 512 GB/s
INTEL
$179
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 5060 Ti 8GB
8 GB VRAM • 448 GB/s
NVIDIA
$379
AmazonNeweggeBayPCPartPicker
NVIDIA RTX 5060
8 GB VRAM • 448 GB/s
NVIDIA
$299
AmazonNeweggeBayPCPartPicker
NVIDIA Tesla K8
8 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M60
8 GB VRAM • 160 GB/s
NVIDIA

Find the best GPU for SOLAR-10.7B

Build Hardware for SOLAR-10.7B

Model Card

View on HuggingFace

We introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks.

▸ SPEC SHEET

SOLAR-10.7B — 10.7B Dense.

▸ SPECIFICATIONS
PARAMETERS
10.7B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
4K tokens
CAPABILITIES
chat
RELEASE DATE
2023-12-13
PROVIDER
Upstage
FAMILY
solar
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q3_K_M45.8 GB88%
Q3_K_L4.36.2 GB90%
IQ4_XS4.466.5 GB92%
Q4_K_S4.676.7 GB93%
Q4_K_M4.897.0 GB94%
Q5_K_S5.577.9 GB96%
Q5_K_M5.78.1 GB96%
Q6_K6.569.3 GB97%
Q8_08.511.9 GB100%
FP161621.9 GB100%
§ 01BENCHMARK SCORES
HumanEval37.2
MMLU-PRO28.3
MATH12.2
IFEval65.0
BBH28.5
GPQA6.5
MUSR11.7
MBPP36.2
§ 02RUN COMMAND

Run SOLAR-10.7B locally with Ollama — needs 7.0 GB VRAM at Q4_K_M:

$ollama run solar:10.7b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA RTX 4060 Ti 8GB
8 GB · 288 GB/s
NVIDIA RTX 4060
8 GB · 272 GB/s
NVIDIA RTX 3070 Ti
8 GB · 608 GB/s
NVIDIA RTX 3070
8 GB · 448 GB/s
NVIDIA RTX 3060 Ti
8 GB · 448 GB/s
NVIDIA RTX 3050 8GB
8 GB · 224 GB/s
AMD RX 7600
8 GB · 288 GB/s
AMD RX 6650 XT
8 GB · 280 GB/s
Intel Arc A750
8 GB · 512 GB/s
Apple M1 (8GB)
8 GB · 68 GB/s
Apple M2 (8GB)
8 GB · 100 GB/s
Apple M3 (8GB)
8 GB · 100 GB/s
NVIDIA RTX 2080 SUPER
8 GB · 496 GB/s
NVIDIA RTX 2080
8 GB · 448 GB/s
NVIDIA RTX 2070 SUPER
8 GB · 448 GB/s