RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can I run Mistral 7B Instruct v0.1 locally?

Mistral 7B Instruct 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.

5.5 GBQ4_K_M · 8K context
RTX 4060smallest consumer GPU that fits
M1 16GBsmallest Mac that fits
32Kmax context
GQAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from TheBloke/Mistral-7B-Instruct-v0.1-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx
2-bit (Q2_K) •rough3.8 GB4.3 GB7.3 GB
3-bit (Q3_K_M) •usable4.2 GB4.7 GB7.7 GB
4-bit (Q4_K_M) •good, most popular5.0 GB5.5 GB8.5 GB
5-bit (Q5_K_M) •very good5.7 GB6.2 GB9.2 GB
6-bit (Q6_K) •near lossless6.5 GB7.0 GB10.0 GB
8-bit (Q8_0) •effectively lossless8.1 GB8.6 GB11.6 GB
16-bit (F16/BF16)original weights14.4 GB14.9 GB17.9 GB

Which GPUs and Macs run Mistral 7B Instruct 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).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)
RTX 3060 12GB12 GBFitsQ8_08.6 GB47details
RTX 4060 Ti 16GB16 GBFitsQ8_08.6 GB37details
RTX 309024 GBFitsF1614.9 GB65details
RTX 409024 GBFitsF1614.9 GB70details
RTX 509032 GBFitsF1614.9 GB124details
RTX 5070 Ti16 GBFitsQ8_08.6 GB116details
RX 7900 XTX24 GBFitsF1614.9 GB66details
Mac M4 Pro 48GB48 GBFitsF1614.9 GB19details
Mac M4 Max 128GB128 GBFitsF1614.9 GB38details
Mac M3 Ultra 512GB512 GBFitsF1614.9 GB57details
DGX Spark128 GBFitsF1614.9 GB19details
RTX 407012 GBFitsQ8_08.6 GB65details
RTX 5060 Ti 16GB16 GBFitsQ8_08.6 GB58details
RTX 40608 GBFitsQ5_K_M6.2 GB53details
Arc B58012 GBFitsQ8_08.6 GB59details
RTX 3060 Ti8 GBFitsQ5_K_M6.2 GB87details
RTX 30708 GBFitsQ5_K_M6.2 GB87details
RTX 3080 10GB10 GBFitsQ6_K7.0 GB128details
RTX 3080 12GB12 GBFitsQ8_08.6 GB119details
RTX 3090 Ti24 GBFitsF1614.9 GB70details
RTX 4060 Ti 8GB8 GBFitsQ5_K_M6.2 GB56details
RTX 4070 Super12 GBFitsQ8_08.6 GB65details
RTX 4070 Ti12 GBFitsQ8_08.6 GB65details
RTX 4070 Ti Super16 GBFitsQ8_08.6 GB87details
RTX 408016 GBFitsQ8_08.6 GB93details
RTX 4080 Super16 GBFitsQ8_08.6 GB96details
RTX 50608 GBFitsQ5_K_M6.2 GB87details
RTX 507012 GBFitsQ8_08.6 GB87details
RTX 508016 GBFitsQ8_08.6 GB125details
2x RTX 30902×24 GBFitsF1614.9 GB65details
2x RTX 40902×24 GBFitsF1614.9 GB70details
2x RTX 50902×32 GBFitsF1614.9 GB124details
RTX A600048 GBFitsF1614.9 GB53details
RTX 6000 Ada48 GBFitsF1614.9 GB66details
RTX PRO 6000 Blackwell96 GBFitsF1614.9 GB124details
L40S48 GBFitsF1614.9 GB60details
A100 40GB40 GBFitsF1614.9 GB107details
A100 80GB80 GBFitsF1614.9 GB141details
H100 PCIe80 GBFitsF1614.9 GB138details
H100 SXM80 GBFitsF1614.9 GB231details
H200141 GBFitsF1614.9 GB331details
RX 76008 GBFitsQ5_K_M6.2 GB56details
RX 7700 XT12 GBFitsQ8_08.6 GB56details
RX 7800 XT16 GBFitsQ8_08.6 GB81details
RX 7900 GRE16 GBFitsQ8_08.6 GB75details
RX 7900 XT20 GBFitsF1614.9 GB55details
RX 907016 GBFitsQ8_08.6 GB83details
RX 9070 XT16 GBFitsQ8_08.6 GB83details
Ryzen AI Max+ 395 128GB128 GBFitsF1614.9 GB18details
Arc A770 16GB16 GBFitsQ8_08.6 GB73details
Mac M1 16GB16 GBFitsQ8_08.6 GB8.8details
Mac M2 24GB24 GBFitsQ8_08.6 GB13details
Mac M3 24GB24 GBFitsQ8_08.6 GB13details
Mac M4 16GB16 GBFitsQ8_08.6 GB16details
Mac M4 32GB32 GBFitsF1614.9 GB8.3details
Mac M1 Pro 32GB32 GBFitsF1614.9 GB14details
Mac M3 Pro 36GB36 GBFitsF1614.9 GB10details
Mac M4 Pro 24GB24 GBFitsQ8_08.6 GB35details
Mac M4 Pro 64GB64 GBFitsF1614.9 GB19details
Mac M1 Max 64GB64 GBFitsF1614.9 GB28details
Mac M2 Max 96GB96 GBFitsF1614.9 GB28details
Mac M3 Max 128GB128 GBFitsF1614.9 GB28details
Mac M4 Max 64GB64 GBFitsF1614.9 GB38details
Mac M2 Ultra 192GB192 GBFitsF1614.9 GB55details
Mac M3 Ultra 256GB256 GBFitsF1614.9 GB57details

Questions

How much VRAM does Mistral 7B Instruct 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 Instruct 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 Instruct 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 v0.1

7.2B · 5.5 GB at 4-bit

Mistral 7B Instruct v0.2

7.2B · 47.7 GB at 4-bit

falcon 7b

7.2B · 9.6 GB at 4-bit

falcon 7b instruct

7.2B · 9.4 GB at 4-bit

Olmo 3 7B Instruct

7.3B · 7.3 GB at 4-bit

Olmo 3 1025 7B

7.3B · 7.3 GB at 4-bit

Model facts

Hugging Face repomistralai/Mistral-7B-Instruct-v0.1
Parameters7,241,732,096 (7.2B)
Layers / hidden size32 / 4096
AttentionGQA; 32 heads, 8 KV heads, head dim 128
KV cache per token (FP16)128.0 KiB
Max context32,768 tokens
Licenseapache-2.0
Released on HFSep 27, 2023
Downloads (30d) / likes108,428 / 1,878

Sources: Hugging Face model API · config.json (mistralai/Mistral-7B-Instruct-v0.1) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.