Hermes 3 Llama 3.1 70B Lorablated — Hardware Requirements & GPU Compatibility
Chat
Hermes 3 Llama 3.1 70B Lorablated is a 70.6B-parameter open language model from mlabonne in the Llama 3 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 43.30 GB of VRAM — see which GPUs and Macs can run it below.
72 downloads
37 likesSpecifications
- Publisher
- mlabonne
- Family
- Llama 3
- Parameters
- 70.6B
- Architecture
- LlamaForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 128,256
- Release Date
- 2024-08-16
Get Started
HuggingFace
How Much VRAM Does Hermes 3 Llama 3.1 70B Lorablated Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 31.0 GB | 73.2 GB | 29.99 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 35.4 GB | 77.6 GB | 34.39 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 43.3 GB | 85.6 GB | 42.33 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 51.2 GB | 93.5 GB | 50.27 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 59.2 GB | 101.5 GB | 58.21 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 71.5 GB | 113.8 GB | 70.55 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 142.1 GB | 184.4 GB | 141.11 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Hermes 3 Llama 3.1 70B Lorablated?
Q4_K_M · 43.3 GBHermes 3 Llama 3.1 70B Lorablated (Q4_K_M) requires 43.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 57+ GB is recommended. Using the full 131K context window can add up to 42.3 GB, bringing total usage to 85.6 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Hermes 3 Llama 3.1 70B Lorablated?
Q4_K_M · 43.3 GB11 devices with unified memory can run Hermes 3 Llama 3.1 70B Lorablated, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Related Models
Frequently Asked Questions
- How much VRAM does Hermes 3 Llama 3.1 70B Lorablated need?
Hermes 3 Llama 3.1 70B Lorablated requires 43.3 GB of VRAM at Q4_K_M, or 142.1 GB at BF16. Full 131K context adds up to 42.3 GB (85.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 70.6B × 4.8 bits ÷ 8 = 42.3 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 43.3 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M43.3 GBQ4_K_M + full context85.6 GB- Can NVIDIA GeForce RTX 5090 run Hermes 3 Llama 3.1 70B Lorablated?
Yes, at Q2_K (31.0 GB) or lower. Higher quantizations like Q3_K_M (35.4 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.
- What's the best quantization for Hermes 3 Llama 3.1 70B Lorablated?
For Hermes 3 Llama 3.1 70B Lorablated, Q4_K_M (43.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (51.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 31.0 GB.
VRAM requirement by quantization
Q2_K31.0 GBQ4_K_M ★43.3 GBQ5_K_M51.2 GBQ6_K59.2 GBQ8_071.5 GBBF16142.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Hermes 3 Llama 3.1 70B Lorablated on a Mac?
Hermes 3 Llama 3.1 70B Lorablated requires at least 31.0 GB at Q2_K, 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 Hermes 3 Llama 3.1 70B Lorablated locally?
Yes — Hermes 3 Llama 3.1 70B Lorablated can run locally on consumer hardware. At Q4_K_M quantization it needs 43.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Hermes 3 Llama 3.1 70B Lorablated?
At Q4_K_M, Hermes 3 Llama 3.1 70B Lorablated can reach ~67 tok/s on AMD Instinct MI300X. 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 ÷ 43.3 × 0.55 = ~67 tok/s
Estimated speed at Q4_K_M (43.3 GB)
~67 tok/s~50 tok/s~42 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Hermes 3 Llama 3.1 70B Lorablated?
At Q4_K_M, the download is about 42.33 GB. The full-precision BF16 version is 141.11 GB. The smallest option (Q2_K) is 29.99 GB.
- Which GPUs can run Hermes 3 Llama 3.1 70B Lorablated?
No single consumer GPU has enough VRAM to run Hermes 3 Llama 3.1 70B Lorablated at Q4_K_M (43.3 GB). Multi-GPU or professional hardware is required.
- Which devices can run Hermes 3 Llama 3.1 70B Lorablated?
11 devices with unified memory can run Hermes 3 Llama 3.1 70B Lorablated at Q4_K_M (43.3 GB), including Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.