Mistral NeMo Minitron 8B Instruct — Hardware Requirements & GPU Compatibility
Chat
Mistral NeMo Minitron 8B Instruct is a 8.4B-parameter open language model from NVIDIA in the Mistral family. It supports a context window of up to 8,192 tokens. At Q4_K_M it needs about 5.68 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~115 tok/s · 8K)Macs from 16 GB (Q4_K_M · ~25 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Mistral NeMo Minitron 8B Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve nvidia/Mistral-NeMo-Minitron-8B-Instruct --max-model-len 8192vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (5 GB headroom) · Q4_K_M
- Generation speed
- ~104 tok/s
- generation speed
- Cost per 1M output tokens
- $0.33
- per 1M output tokens
How Much VRAM Does Mistral NeMo Minitron 8B Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.2 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 8K context · ~156 tok/s | |
| 4.7 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 8K context · ~138 tok/s | |
| 5.7 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~115 tok/s | |
| 6.6 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 8K context · ~99 tok/s | |
| 7.6 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 8K context · ~86 tok/s | |
| 9.1 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 8K context · ~72 tok/s | |
| 17.5 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 8K context · ~38 tok/s |
Selected Q4_K_M
4-bit medium quantization6.7GBat 8K context
- Weights
- 5.0 GB
- KV cache
- 1.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 17.3 GB free · ~115 tok/s
≥50 tok/s needs ≥436 GB/s · RTX 5090 ~205, RTX 3090 Ti ~115
Which Hardware Can Run Mistral NeMo Minitron 8B Instruct?
Q4_K_M · 5.7 GBMistral NeMo Minitron 8B Instruct (Q4_K_M) requires 5.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 8K context window can add up to 1.0 GB, bringing total usage to 6.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run Mistral NeMo Minitron 8B Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
≤ 11 GB
≤ 11 GB tier →fits · 1.3 GB free · up to 8K ctx
16 GPUs · 1 device family
RTX 3080~87Simulate output on RTX 3080RTX 2080 Ti~71Simulate output on RTX 2080 TiRTX 3070 Ti~70Simulate output on RTX 3070 TiOrin Nano~12Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 13.3 GB free · up to 8K ctx
1 GPU
RX 7900 XT~85Simulate output on RX 7900 XT32–40 GB
fits · 25.3 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~205Simulate output on RTX 5090M5 Max36 GB~57Simulate output on Mac Studio M5 Max (36 GB)M532 GB~19Simulate output on MacBook Air 13" M5 (32 GB)Orin~23Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~15Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Mistral NeMo Minitron 8B Instruct
Mistral family · 35 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite Switch 4.1 8BIBM | — | 8.4 GB | ~111 | same size |
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Llm Jp 4.1 8B Thinkingllm-jp | — | 7.6 GB | ~115 | same size |
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| Apertus V1.5 8Bswiss-ai | — | 8.5 GB | ~111 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
Specifications
- Publisher
- NVIDIA
- Family
- Mistral
- Parameters
- 8.4B
- Architecture
- MistralForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2024-10-02
- License
- Other
Frequently Asked Questions
How much VRAM does Mistral NeMo Minitron 8B Instruct need?
Mistral NeMo Minitron 8B Instruct requires 5.7 GB of VRAM at Q4_K_M, or 17.5 GB at BF16. Full 8K context adds up to 1.0 GB (6.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.4B × 4.8 bits ÷ 8 = 5 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 1.7 GB (at full 8K context)
VRAM usage by quantization
What's the best quantization for Mistral NeMo Minitron 8B Instruct?
For Mistral NeMo Minitron 8B Instruct, Q4_K_M (5.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (6.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Mistral NeMo Minitron 8B Instruct on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Mistral NeMo Minitron 8B Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Mistral NeMo Minitron 8B Instruct locally?
Yes — Mistral NeMo Minitron 8B Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Mistral NeMo Minitron 8B Instruct?
At Q4_K_M, Mistral NeMo Minitron 8B Instruct can reach ~845 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~115 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 5.6800 × 0.65 = ~915 tok/s
Estimated speed at Q4_K_M (5.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Mistral NeMo Minitron 8B Instruct?
At Q4_K_M, the download is about 5.05 GB. The full-precision BF16 version is 16.83 GB. The smallest option (Q2_K) is 3.58 GB.
Which GPUs can run Mistral NeMo Minitron 8B Instruct?
52 consumer GPUs can run Mistral NeMo Minitron 8B Instruct at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run Mistral NeMo Minitron 8B Instruct?
151 devices with unified memory can run Mistral NeMo Minitron 8B Instruct at Q4_K_M (5.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.