Can I run Mistral 7B v0.1 locally?
Mistral 7B v0.1 by mistralai has 7.2B parameters. At 4-bit with an 8K context it needs about 5.5 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from bartowski/Hermes-2-Pro-Mistral-7B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx |
|---|---|---|---|---|
| 2-bit (Q2_K) • | rough | 3.5 GB | 4.0 GB | 7.0 GB |
| 3-bit (Q3_K_M) • | usable | 4.2 GB | 4.7 GB | 7.7 GB |
| 4-bit (Q4_K_M) • | good, most popular | 5.0 GB | 5.5 GB | 8.5 GB |
| 5-bit (Q5_K_M) • | very good | 5.7 GB | 6.2 GB | 9.2 GB |
| 6-bit (Q6_K) • | near lossless | 6.5 GB | 7.0 GB | 10.0 GB |
| 8-bit (Q8_0) • | effectively lossless | 8.1 GB | 8.6 GB | 11.6 GB |
| 16-bit (F16/BF16) | original weights | 14.4 GB | 14.9 GB | 17.9 GB |
Which GPUs and Macs run Mistral 7B v0.1?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
| Hardware | Memory | Fits? | Best quant | Needs | Max tok/s (est.) | |
|---|---|---|---|---|---|---|
| RTX 3060 12GB | 12 GB | Fits | Q8_0 | 8.6 GB | 47 | details |
| RTX 4060 Ti 16GB | 16 GB | Fits | Q8_0 | 8.6 GB | 37 | details |
| RTX 3090 | 24 GB | Fits | F16 | 14.9 GB | 65 | details |
| RTX 4090 | 24 GB | Fits | F16 | 14.9 GB | 70 | details |
| RTX 5090 | 32 GB | Fits | F16 | 14.9 GB | 124 | details |
| RTX 5070 Ti | 16 GB | Fits | Q8_0 | 8.6 GB | 116 | details |
| RX 7900 XTX | 24 GB | Fits | F16 | 14.9 GB | 66 | details |
| Mac M4 Pro 48GB | 48 GB | Fits | F16 | 14.9 GB | 19 | details |
| Mac M4 Max 128GB | 128 GB | Fits | F16 | 14.9 GB | 38 | details |
| Mac M3 Ultra 512GB | 512 GB | Fits | F16 | 14.9 GB | 57 | details |
| DGX Spark | 128 GB | Fits | F16 | 14.9 GB | 19 | details |
| RTX 4070 | 12 GB | Fits | Q8_0 | 8.6 GB | 65 | details |
| RTX 5060 Ti 16GB | 16 GB | Fits | Q8_0 | 8.6 GB | 58 | details |
| RTX 4060 | 8 GB | Fits | Q5_K_M | 6.2 GB | 53 | details |
| Arc B580 | 12 GB | Fits | Q8_0 | 8.6 GB | 59 | details |
| RTX 3060 Ti | 8 GB | Fits | Q5_K_M | 6.2 GB | 87 | details |
| RTX 3070 | 8 GB | Fits | Q5_K_M | 6.2 GB | 87 | details |
| RTX 3080 10GB | 10 GB | Fits | Q6_K | 7.0 GB | 128 | details |
| RTX 3080 12GB | 12 GB | Fits | Q8_0 | 8.6 GB | 119 | details |
| RTX 3090 Ti | 24 GB | Fits | F16 | 14.9 GB | 70 | details |
| RTX 4060 Ti 8GB | 8 GB | Fits | Q5_K_M | 6.2 GB | 56 | details |
| RTX 4070 Super | 12 GB | Fits | Q8_0 | 8.6 GB | 65 | details |
| RTX 4070 Ti | 12 GB | Fits | Q8_0 | 8.6 GB | 65 | details |
| RTX 4070 Ti Super | 16 GB | Fits | Q8_0 | 8.6 GB | 87 | details |
| RTX 4080 | 16 GB | Fits | Q8_0 | 8.6 GB | 93 | details |
| RTX 4080 Super | 16 GB | Fits | Q8_0 | 8.6 GB | 96 | details |
| RTX 5060 | 8 GB | Fits | Q5_K_M | 6.2 GB | 87 | details |
| RTX 5070 | 12 GB | Fits | Q8_0 | 8.6 GB | 87 | details |
| RTX 5080 | 16 GB | Fits | Q8_0 | 8.6 GB | 125 | details |
| 2x RTX 3090 | 2×24 GB | Fits | F16 | 14.9 GB | 65 | details |
| 2x RTX 4090 | 2×24 GB | Fits | F16 | 14.9 GB | 70 | details |
| 2x RTX 5090 | 2×32 GB | Fits | F16 | 14.9 GB | 124 | details |
| RTX A6000 | 48 GB | Fits | F16 | 14.9 GB | 53 | details |
| RTX 6000 Ada | 48 GB | Fits | F16 | 14.9 GB | 66 | details |
| RTX PRO 6000 Blackwell | 96 GB | Fits | F16 | 14.9 GB | 124 | details |
| L40S | 48 GB | Fits | F16 | 14.9 GB | 60 | details |
| A100 40GB | 40 GB | Fits | F16 | 14.9 GB | 107 | details |
| A100 80GB | 80 GB | Fits | F16 | 14.9 GB | 141 | details |
| H100 PCIe | 80 GB | Fits | F16 | 14.9 GB | 138 | details |
| H100 SXM | 80 GB | Fits | F16 | 14.9 GB | 231 | details |
| H200 | 141 GB | Fits | F16 | 14.9 GB | 331 | details |
| RX 7600 | 8 GB | Fits | Q5_K_M | 6.2 GB | 56 | details |
| RX 7700 XT | 12 GB | Fits | Q8_0 | 8.6 GB | 56 | details |
| RX 7800 XT | 16 GB | Fits | Q8_0 | 8.6 GB | 81 | details |
| RX 7900 GRE | 16 GB | Fits | Q8_0 | 8.6 GB | 75 | details |
| RX 7900 XT | 20 GB | Fits | F16 | 14.9 GB | 55 | details |
| RX 9070 | 16 GB | Fits | Q8_0 | 8.6 GB | 83 | details |
| RX 9070 XT | 16 GB | Fits | Q8_0 | 8.6 GB | 83 | details |
| Ryzen AI Max+ 395 128GB | 128 GB | Fits | F16 | 14.9 GB | 18 | details |
| Arc A770 16GB | 16 GB | Fits | Q8_0 | 8.6 GB | 73 | details |
| Mac M1 16GB | 16 GB | Fits | Q8_0 | 8.6 GB | 8.8 | details |
| Mac M2 24GB | 24 GB | Fits | Q8_0 | 8.6 GB | 13 | details |
| Mac M3 24GB | 24 GB | Fits | Q8_0 | 8.6 GB | 13 | details |
| Mac M4 16GB | 16 GB | Fits | Q8_0 | 8.6 GB | 16 | details |
| Mac M4 32GB | 32 GB | Fits | F16 | 14.9 GB | 8.3 | details |
| Mac M1 Pro 32GB | 32 GB | Fits | F16 | 14.9 GB | 14 | details |
| Mac M3 Pro 36GB | 36 GB | Fits | F16 | 14.9 GB | 10 | details |
| Mac M4 Pro 24GB | 24 GB | Fits | Q8_0 | 8.6 GB | 35 | details |
| Mac M4 Pro 64GB | 64 GB | Fits | F16 | 14.9 GB | 19 | details |
| Mac M1 Max 64GB | 64 GB | Fits | F16 | 14.9 GB | 28 | details |
| Mac M2 Max 96GB | 96 GB | Fits | F16 | 14.9 GB | 28 | details |
| Mac M3 Max 128GB | 128 GB | Fits | F16 | 14.9 GB | 28 | details |
| Mac M4 Max 64GB | 64 GB | Fits | F16 | 14.9 GB | 38 | details |
| Mac M2 Ultra 192GB | 192 GB | Fits | F16 | 14.9 GB | 55 | details |
| Mac M3 Ultra 256GB | 256 GB | Fits | F16 | 14.9 GB | 57 | details |
Questions
How much VRAM does Mistral 7B v0.1 need?
About 5.5 GB at 4-bit (Q4_K_M) with an 8K context: 4.1 GB of weights (real GGUF file size), 1.0 GB of KV cache and 0.5 GB of runtime overhead. At 8-bit it needs about 8.6 GB.
What is the smallest GPU that runs Mistral 7B v0.1?
At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).
Can I run Mistral 7B v0.1 on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Mistral 7B Instruct v0.2
7.2B · 47.7 GB at 4-bitMistral 7B Instruct v0.1
7.2B · 5.5 GB at 4-bitfalcon 7b
7.2B · 9.6 GB at 4-bitfalcon 7b instruct
7.2B · 9.4 GB at 4-bitOlmo 3 7B Instruct
7.3B · 7.3 GB at 4-bitOlmo 3 1025 7B
7.3B · 7.3 GB at 4-bitModel facts
| Hugging Face repo | mistralai/Mistral-7B-v0.1 |
| Parameters | 7,241,732,096 (7.2B) |
| Layers / hidden size | 32 / 4096 |
| Attention | GQA; 32 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 128.0 KiB |
| Max context | 32,768 tokens |
| License | apache-2.0 |
| Released on HF | Sep 20, 2023 |
| Downloads (30d) / likes | 443,042 / 4,232 |
Sources: Hugging Face model API · config.json (mistralai/Mistral-7B-v0.1) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.