<!-- Markdown mirror of https://getrigbase.com/models/hermes-4-3-36b/ . Source of truth is the HTML page. Data licence: CC BY 4.0, please cite RigBase (https://getrigbase.com/models/hermes-4-3-36b/). -->
Source: https://getrigbase.com/models/hermes-4-3-36b/
Last updated: 2026-11-15

[Models](https://getrigbase.com/models/) / Hermes 4.3 36B

# Best home rig for Hermes 4.3 36B

Quick answer

**How much VRAM does Hermes 4.3 36B need?**
The weights are about 22.0 GB at Q4_K_M (36B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is RTX Spark N1X (82 GB) at 12.0 tok/s.

**What is the fastest measured hardware for Hermes 4.3 36B?**
RTX Spark N1X: 12.0 tok/s generation (llama.cpp b12110 (CUDA, Windows on Arm), Q4_K_M (21.8 GB)), from https://dev.to/maruhana/a-120b-model-ran-about-4x-faster-than-a-27b-one-8-local-llms-on-a-surface-laptop-ultra-5cpg.

Last updated: 15 Nov 2026

Legacy model 36B dense 1 measured result fastest plain decode: 12.0 tok/s  [model info ↗](https://huggingface.co/NousResearch/Hermes-4.3-36B)

Older model. For current picks see [current models](https://getrigbase.com/models/).

Real, measured generation speeds for Hermes 4.3 36B on home hardware, fastest first. Different quants/engines aren't directly comparable.

| Build | Quant | Engine | tok/s | Prompt processing (tok/s) | Cost | Source |
|---|---|---|---|---|---|---|
| [Surface Laptop Ultra (RTX Spark N1X, 128 GB): 8 models on llama.cpp b12110, Flint 104.8 tok/s, gpt-oss 120B 64.2, Qwen3.8 27B 16.5 (maruhana)](https://getrigbase.com/builds/surface-laptop-ultra-rtx-spark-n1x-8-models-llamacpp-maruhana/) | Q4_K_M (21.8 GB) | llama.cpp b12110 (CUDA, Windows on Arm) | **12.0** | 733 @512 · est. TTFT @8k ≈11.2 s* |  | [dev.to ↗](https://dev.to/maruhana/a-120b-model-ran-about-4x-faster-than-a-27b-one-8-local-llms-on-a-surface-laptop-ultra-5cpg) |

Prompt processing = prefill speed reported by the source, @ prompt length. * est. TTFT @8k is calculated from measured prefill, not measured. [Why it matters](https://getrigbase.com/can-it-run/#prefill).
Ad · this space is available **Sponsor this spot: reach people building local AI rigs.** One clearly-labeled slot per page, no tracking scripts.  [Sponsor this spot →](https://getrigbase.com/advertise/#inquiry)

**Rent before you buy:** try this model on a cloud GPU for a few dollars first: [Runpod](https://runpod.io?ref=77qcpl2c) (referral link; sign up with Google to get the new-user bonus)

## Memory math: how much VRAM / RAM does Hermes 4.3 36B need?

Hermes 4.3 36B has **36B parameters** ([source](https://huggingface.co/NousResearch/Hermes-4.3-36B): Nous Research model card, 36B dense). Weight size = parameters × bits-per-weight ÷ 8, before context (KV cache) and runtime overhead.

| Format | Bits/weight | Weights | Smallest common memory size that holds the weights alone |
|---|---|---|---|
| Q8_0 | 8.50 | 38.3 GB | 48 GB |
| Q6_K | 6.56 | 29.5 GB | 32 GB |
| Q5_K_M | 5.70 | 25.7 GB | 32 GB |
| Q4_K_M | 4.89 | **22.0 GB** | 24 GB |
| Q3_K_M | 4.00 | 18.0 GB | 24 GB |
| Q2_K | 3.16 | 14.2 GB | 16 GB |

Bits-per-weight for GGUF quants are llama.cpp's own figures ([llama.cpp quantize README](https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md)). "As measured" rows apply the source's stated bits-per-weight to the parameter count; real files differ slightly because some layers stay at higher precision. Try other combinations in the [VRAM calculator](https://getrigbase.com/can-it-run/).

## FAQ

### How much VRAM does Hermes 4.3 36B need?

The weights are about 22.0 GB at Q4_K_M (36B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is RTX Spark N1X (82 GB) at 12.0 tok/s.

### What is the fastest measured hardware for Hermes 4.3 36B?

RTX Spark N1X: 12.0 tok/s generation (llama.cpp b12110 (CUDA, Windows on Arm), Q4_K_M (21.8 GB)), from https://dev.to/maruhana/a-120b-model-ran-about-4x-faster-than-a-27b-one-8-local-llms-on-a-surface-laptop-ultra-5cpg.

Related: [what GPU do you need for 2026 models](https://getrigbase.com/guides/what-gpu-for-qwen3-6-gemma-4-gpt-oss/) · [all builds](https://getrigbase.com/builds/)
