Mistral 7B Instruct v0.3 — Hardware Requirements & GPU Compatibility
Chat
Mistral 7B Instruct v0.3 is the latest instruction-tuned release of Mistral AI's original 7-billion-parameter model, delivering meaningful improvements in instruction following, function calling, and multilingual support over its predecessors. With an extended 32K-token vocabulary and refined chat capabilities, v0.3 remains one of the most capable sub-10B models available. At 7.2 billion parameters it sits comfortably in the sweet spot for local inference, running well on GPUs with 6–8 GB of VRAM at full precision and even on 4 GB cards with 4-bit quantization. It is an excellent default choice for anyone getting started with local LLMs who wants strong conversational performance without heavy hardware.
3.1M downloads
2.6K likesSpecifications
- Publisher
- Mistral AI
- Family
- Mistral
- Parameters
- 7.2B
- Architecture
- MistralForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 32,768
- Release Date
- 2024-05-22
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Mistral 7B Instruct v0.3 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 3.6 GB | 7.7 GB | 3.08 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 3.7 GB | 7.8 GB | 3.17 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 4.1 GB | 8.1 GB | 3.53 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 4.2 GB | 8.2 GB | 3.62 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 4.9 GB | 8.9 GB | 4.35 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 5.7 GB | 9.8 GB | 5.16 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 6.5 GB | 10.6 GB | 5.98 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 7.8 GB | 11.8 GB | 7.25 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 7B Instruct v0.3?
Q4_K_M · 4.9 GBMistral 7B Instruct v0.3 (Q4_K_M) requires 4.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 33K context window can add up to 4.0 GB, bringing total usage to 8.9 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Mistral 7B Instruct v0.3?
Q4_K_M · 4.9 GB59 devices with unified memory can run Mistral 7B Instruct v0.3, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Apple iPhone 17 Pro.
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download Mistral 7B Instruct v0.3
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 7B Instruct v0.3 need?
Mistral 7B Instruct v0.3 requires 4.9 GB of VRAM at Q4_K_M, or 15.1 GB at BF16. Full 33K context adds up to 4.0 GB (8.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.2B × 4.8 bits ÷ 8 = 4.3 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.6 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M4.9 GBQ4_K_M + full context8.9 GB- What's the best quantization for Mistral 7B Instruct v0.3?
For Mistral 7B Instruct v0.3, Q4_K_M (4.9 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XS at 2.7 GB.
VRAM requirement by quantization
IQ2_XS2.7 GBIQ3_M3.8 GBIQ4_NL4.7 GBQ4_K_M ★4.9 GBQ5_15.5 GBBF1615.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Mistral 7B Instruct v0.3 on a Mac?
Mistral 7B Instruct v0.3 requires at least 2.7 GB at IQ2_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 7B Instruct v0.3 locally?
Yes — Mistral 7B Instruct v0.3 can run locally on consumer hardware. At Q4_K_M quantization it needs 4.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Mistral 7B Instruct v0.3?
At Q4_K_M, Mistral 7B Instruct v0.3 can reach ~894 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~133 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 ÷ 4.9 × 0.65 = ~1057 tok/s
Estimated speed at Q4_K_M (4.9 GB)
~1057 tok/s~133 tok/s~1057 tok/s~894 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Mistral 7B Instruct v0.3?
At Q4_K_M, the download is about 4.35 GB. The full-precision BF16 version is 14.50 GB. The smallest option (IQ2_XS) is 2.17 GB.
- Which GPUs can run Mistral 7B Instruct v0.3?
50 consumer GPUs can run Mistral 7B Instruct v0.3 at Q4_K_M (4.9 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Mistral 7B Instruct v0.3?
59 devices with unified memory can run Mistral 7B Instruct v0.3 at Q4_K_M (4.9 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.