Hermes 2 Pro Mistral 7B on Apple M6 (16 GB)

Can the Apple M6 (16 GB) run Hermes 2 Pro Mistral 7B?

Yes, it runs well

Runs well. At Q4_K_M it needs about 6.9 GB of 10.7 GB usable, with an estimated speed of 22.3 tok/s.

Best quant: Q4_K_M
Generation speed: 22.3 tok/s
Prompt processing: 488 tok/s
First token (1K prompt): 2.1 s
Largest safe context: 32K

Best app to run it on the Apple M6 (16 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Runs the MLX build, typically 20–35% faster than GGUF for a model with 7.2B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Hermes 2 Pro Mistral 7B in LM Studio

MLX LM Runs the MLX build, typically 20–35% faster than GGUF for a model with 7.2B active parameters on Apple silicon.
Jan Runs the MLX build, typically 20–35% faster than GGUF for a model with 7.2B active parameters on Apple silicon.

Want an agent? Hermes 2 Pro Mistral 7B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Hermes 2 Pro Mistral 7B

Recommended for the Apple M6 (16 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M file (opens in a new tab)

huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF (opens in a new tab)

ollama run hf.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF:Q4_K_M

Original weights · Hugging Face

Full-precision files from Nous Research, for fine-tuning, vLLM, Transformers.

huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the Apple M6 (16 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	15.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	11.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	66.6 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Apple M6 (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.4 GB	10.7 GB	36.7 tok/s	Runs great	25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	6.1 GB	10.7 GB	28.9 tok/s	Runs well	30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	6.9 GB	10.7 GB	22.3 tok/s	Runs well	34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	7.7 GB	10.7 GB	18.5 tok/s	Runs well	34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	8.5 GB	10.7 GB	15.5 tok/s	Runs well	35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	10.2 GB	10.7 GB	11.4 tok/s	Runs welltight fit	36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	17.0 GB	10.7 GB	—	Won't run	36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 43.5 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 F16 · 40.1 tok/s · Runs great
35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q6_K · 41.0 tok/s · Runs great
35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q6_K · 42.4 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 47.6 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 58.0 tok/s · Runs great

Quick answers

How much memory does Hermes 2 Pro Mistral 7B need on the M6 16GB?

At Q4_K_M it needs about 6.9 GB. The M6 16GB has 10.7 GB usable.

How fast is Hermes 2 Pro Mistral 7B on the M6 16GB?

About 22.3 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Hermes 2 Pro Mistral 7B should I use on the M6 16GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.