Hermes-4-70B GGUF size and VRAM requirements

⬇ 13,997 ❤ 11
Parameters70.55B
Context131,072

lmstudio-community/Hermes-4-70B-GGUF is a very large language model with 70.55 billion parameters, built on the llama architecture. It has been downloaded 13,997 times.

To run lmstudio-community/Hermes-4-70B-GGUF locally at a 4,096-token context, its quantized versions need between 36.64 GB (Q3_K_L, lowest quality) and 71.88 GB (Q8_0, highest quality) of memory, weights plus KV cache and a system margin included.

→ Guide: How much VRAM do you need?

GGUF file size and memory by quantization

Compare real GGUF weight sizes, estimated KV cache and total memory for Q4, Q5, Q8 and every quantization published in this repository.

Quant.Bits QualityWeights KVTotal Speed~Verdict
Q3_K_L 4.21 Good 34.59 GB 1.25 GB 36.64 GB Insufficient
Q4_K_M 4.82 Good 39.6 GB 1.25 GB 41.65 GB Insufficient
Q6_K 6.56 Excellent 53.91 GB 1.25 GB 55.96 GB Insufficient
Q8_0 8.5 Excellent 69.83 GB 1.25 GB 71.88 GB Insufficient

KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.

Frequently asked questions

How much VRAM do you need to run lmstudio-community/Hermes-4-70B-GGUF?

You need about 41.65 GB of VRAM to run lmstudio-community/Hermes-4-70B-GGUF entirely on the GPU using the Q4_K_M quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run lmstudio-community/Hermes-4-70B-GGUF on an 8 GB GPU?

No. lmstudio-community/Hermes-4-70B-GGUF does not fit on an 8 GB GPU, even with the smallest quantization and system RAM offloading.

Can I run lmstudio-community/Hermes-4-70B-GGUF on a 16 GB GPU?

Partially. lmstudio-community/Hermes-4-70B-GGUF only fits on a 16 GB GPU by offloading part of it to system RAM (with Q4_K_M), which runs but is slower.

Can I run lmstudio-community/Hermes-4-70B-GGUF on a 24 GB GPU?

Partially. lmstudio-community/Hermes-4-70B-GGUF only fits on a 24 GB GPU by offloading part of it to system RAM (with Q8_0), which runs but is slower.

What is the best quantization for lmstudio-community/Hermes-4-70B-GGUF?

If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.