Mistral 7B Instruct v0.3 on AMD Ryzen AI Max+ PRO 495 (192 GB)

Can the AMD Ryzen AI Max+ PRO 495 (192 GB) run Mistral 7B Instruct v0.3?

Yes, it runs great

Runs great. At Q4_K_M it needs about 18.8 GB of 159 GB usable, with an estimated speed of 39.8 tok/s.

Best quant: Q4_K_M
Generation speed: 39.8 tok/s
Prompt processing: 5,251 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 32K

Best app to run it on the AMD Ryzen AI Max+ PRO 495 (192 GB)

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull bartowski/Mistral-7B-Instruct-v0.3-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull bartowski/Mistral-7B-Instruct-v0.3-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

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 Mistral 7B Instruct v0.3

Recommended for the AMD Ryzen AI Max+ PRO 495 (192 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run mistral:7b-instruct-q4_K_M

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/bartowski/Mistral-7B-Instruct-v0.3-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Mistral-7B-Instruct-v0.3-GGUF:Q4_K_M

Original weights · Hugging Face

Full-precision files from Mistral AI, for fine-tuning, vLLM, Transformers.

huggingface.co/mistralai/Mistral-7B-Instruct-v0.3 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Mistral AI. The weights themselves download from Hugging Face.

github.com/mistralai/mistral-inference (opens in a new tab)

Mistral AI’s official inference code.

git clone https://github.com/mistralai/mistral-inference

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

How it’s rated

Quality 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (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 great: How well it runs on the AMD Ryzen AI Max+ PRO 495 (192 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.	16.2 / 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.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	2.7 / 15
Match score	58.9 / 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 AMD Ryzen AI Max+ PRO 495 (192 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	17.3 GB	159 GB	65.4 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	18.0 GB	159 GB	51.5 tok/s	Runs great	31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	18.8 GB	159 GB	39.8 tok/s	Runs great	36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	19.6 GB	159 GB	32.9 tok/s	Runs great	36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	20.4 GB	159 GB	27.6 tok/s	Runs well	37Basic quality (D) · 37 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	22.1 GB	159 GB	20.3 tok/s	Runs well	38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	28.9 GB	159 GB	9.3 tok/s	Slow	38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (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

38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 43.4 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 F16 · 40.0 tok/s · Runs great
37Basic quality (D) · 37 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 · 40.9 tok/s · Runs great
37Basic quality (D) · 37 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 · 42.3 tok/s · Runs great
38Basic quality (D) · 38 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. AMD Radeon RX 9070 XT Q8_0 · 47.5 tok/s · Runs great
38Basic quality (D) · 38 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 Ti SUPER Q8_0 · 57.9 tok/s · Runs great

Quick answers

How much memory does Mistral 7B Instruct v0.3 need on the AMD Ryzen AI Max+ PRO 495 192GB?

At Q4_K_M it needs about 18.8 GB. The AMD Ryzen AI Max+ PRO 495 192GB has 159 GB usable.

How fast is Mistral 7B Instruct v0.3 on the AMD Ryzen AI Max+ PRO 495 192GB?

About 39.8 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Mistral 7B Instruct v0.3 should I use on the AMD Ryzen AI Max+ PRO 495 192GB?

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.