Mistral Nemo Base 2407 — Hardware Requirements & GPU Compatibility
Chat
Mistral-Nemo-Base-2407 is a 12-billion-parameter pretrained base language model jointly developed by Mistral AI and NVIDIA, intended as a drop-in replacement for the earlier Mistral 7B rather than a chat assistant; it has not been instruction-tuned or aligned, and the card notes it carries no built-in moderation mechanisms. It uses a standard transformer architecture with grouped-query attention and SwiGLU activations, and was trained on a large share of multilingual and code data across nine languages. At 12 billion parameters it fits comfortably on a single consumer GPU once quantized. Context length is 131,072 tokens (a 128k window). It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in July 2024, alongside an instruction-tuned Nemo variant.
122.6K downloads
356 likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 12.2B
- Architecture
- MistralForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2024-07-18
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Mistral Nemo Base 2407 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 5.9 GB | 32.4 GB | 5.21 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 6.1 GB | 32.5 GB | 5.36 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 6.7 GB | 33.1 GB | 5.97 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 8.1 GB | 34.5 GB | 7.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 9.4 GB | 35.9 GB | 8.73 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 10.8 GB | 37.3 GB | 10.10 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 13.0 GB | 39.4 GB | 12.25 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Mistral Nemo Base 2407?
Q4_K_M · 8.1 GBMistral Nemo Base 2407 (Q4_K_M) requires 8.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 11+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 34.5 GB. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Mistral Nemo Base 2407?
Q4_K_M · 8.1 GB49 devices with unified memory can run Mistral Nemo Base 2407, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Mistral Nemo Base 2407
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Mistral Nemo Base 2407 need?
Mistral Nemo Base 2407 requires 8.1 GB of VRAM at Q4_K_M, or 25.2 GB at BF16. Full 131K context adds up to 26.4 GB (34.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 12.2B × 4.8 bits ÷ 8 = 7.3 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 27.2 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M8.1 GBQ4_K_M + full context34.5 GB- Can NVIDIA GeForce RTX 4090 run Mistral Nemo Base 2407?
Yes, at Q8_0 (13.0 GB) or lower. Higher quantizations like BF16 (25.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Mistral Nemo Base 2407?
For Mistral Nemo Base 2407, Q4_K_M (8.1 GB) offers the best balance of quality and VRAM usage. Q5_K_S (9.1 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 5.8 GB.
VRAM requirement by quantization
IQ3_XS5.8 GBIQ3_M6.2 GBIQ4_XS7.3 GBQ4_K_M ★8.1 GBQ5_K_M9.4 GBBF1625.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Mistral Nemo Base 2407 on a Mac?
Mistral Nemo Base 2407 requires at least 5.8 GB at IQ3_XS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Mistral Nemo Base 2407 locally?
Yes — Mistral Nemo Base 2407 can run locally on consumer hardware. At Q4_K_M quantization it needs 8.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Mistral Nemo Base 2407?
At Q4_K_M, Mistral Nemo Base 2407 can reach ~595 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~81 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 ÷ 8.1 × 0.65 = ~644 tok/s
Estimated speed at Q4_K_M (8.1 GB)
~644 tok/s~81 tok/s~644 tok/s~595 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Mistral Nemo Base 2407?
At Q4_K_M, the download is about 7.35 GB. The full-precision BF16 version is 24.50 GB. The smallest option (IQ3_XS) is 5.05 GB.
- Which GPUs can run Mistral Nemo Base 2407?
40 consumer GPUs can run Mistral Nemo Base 2407 at Q4_K_M (8.1 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Mistral Nemo Base 2407?
52 devices with unified memory can run Mistral Nemo Base 2407 at Q4_K_M (8.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.