SOLAR 10.7B Instruct v1.0 — Hardware Requirements & GPU Compatibility
Chat
SOLAR 10.7B Instruct v1.0 is a 10.7B-parameter open language model from Upstage in the Solar family. It supports a context window of up to 4,096 tokens. At FP16 it needs about 22.10 GB of VRAM — see which GPUs and Macs can run it below.
26.6K downloads
649 likesSpecifications
- Publisher
- Upstage
- Family
- Solar
- Parameters
- 10.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-09-10
- License
- CC BY-NC 4.0
Get Started
HuggingFace
How Much VRAM Does SOLAR 10.7B Instruct v1.0 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| FP16 | 16.00 | 22.1 GB | 22.5 GB | 21.40 GB | Full half-precision — baseline for inference |
Which GPUs Can Run SOLAR 10.7B Instruct v1.0?
FP16 · 22.1 GBSOLAR 10.7B Instruct v1.0 (FP16) requires 22.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 29+ GB is recommended. Using the full 4K context window can add up to 0.4 GB, bringing total usage to 22.5 GB. 5 GPUs can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Which Devices Can Run SOLAR 10.7B Instruct v1.0?
FP16 · 22.1 GB21 devices with unified memory can run SOLAR 10.7B Instruct v1.0, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does SOLAR 10.7B Instruct v1.0 need?
SOLAR 10.7B Instruct v1.0 requires 22.1 GB of VRAM at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 10.7B × 16 bits ÷ 8 = 21.4 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.1 GB (at full 4K context)
VRAM usage by quantization
FP1622.1 GBFP16 + full context22.5 GB- Can I run SOLAR 10.7B Instruct v1.0 on a Mac?
SOLAR 10.7B Instruct v1.0 requires at least 22.1 GB at FP16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run SOLAR 10.7B Instruct v1.0 locally?
Yes — SOLAR 10.7B Instruct v1.0 can run locally on consumer hardware. At FP16 quantization it needs 22.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is SOLAR 10.7B Instruct v1.0?
At FP16, SOLAR 10.7B Instruct v1.0 can reach ~132 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~30 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 22.1 × 0.55 = ~132 tok/s
Estimated speed at FP16 (22.1 GB)
~132 tok/s~30 tok/s~99 tok/s~82 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of SOLAR 10.7B Instruct v1.0?
At FP16, the download is about 21.40 GB.
- Which GPUs can run SOLAR 10.7B Instruct v1.0?
5 consumer GPUs can run SOLAR 10.7B Instruct v1.0 at FP16 (22.1 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run SOLAR 10.7B Instruct v1.0?
21 devices with unified memory can run SOLAR 10.7B Instruct v1.0 at FP16 (22.1 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.