v2.2 · 2026-06-12
Mistral 7B Instruct v0.3
mistral-7b-instruct-v0-3
Mistral 7B Instruct v0.3 is a 7B text chat model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.
PROVIDER
Mistral AI
FAMILY
mistral
MODEL TYPE
text-chat
PARAMETERS
7B
MODALITIES
text
ARCHITECTURE
decoder-only Transformer (MistralForCausalLM)
CONTEXT WINDOW
32,768 tokens
TRAINING TOKENS
—
RELEASE DATE
2024-05-22
GGUF REPOSITORIES
bartowski/Mistral-7B-Instruct-v0.3-GGUF community conversion
Community GGUF conversion with Q4_K_M, Q5_K_M and Q8_0 file-size table.
SETUP HINTS
OLLAMA
ollama run mistral:7b-instruct-v0.3-q4_K_MLM STUDIO
Use bartowski/Mistral-7B-Instruct-v0.3-GGUF and select Q4_K_M or Q5_K_M.
LLAMA.CPP
llama-server -hf bartowski/Mistral-7B-Instruct-v0.3-GGUF:Q4_K_MQUANTIZATION FILE SIZES (GGUF)
Q4_K_M
4.37 GB
Q5_K_M
5.13 GB
Q8_0
7.7 GB
Quantization note: Q4_K_M
RAM / VRAM ESTIMATES
MIN RAM
8 GB
COMFORTABLE RAM
16 GB
MIN VRAM
6 GB
COMFORTABLE VRAM
8 GB
These are conservative local-inference estimates, not official hardware requirements.
HARDWARE FIT
CPU only (no GPU)
yes
8 GB RAM
limited
16 GB RAM
comfortable
32 GB RAM
comfortable
8 GB VRAM
good
12 GB VRAM
comfortable
24 GB VRAM
comfortable
Apple Silicon (unified memory)
comfortable
Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.
BEST FOR
·permissively licensed 7B chat
·function-calling experiments
·fast local instruct use
·commercial applications needing Apache-2.0 weights
AVOID IF
·you need a large context window above 32k
·you need strongest current 7B-class quality
·your prompt design depends on a dedicated system prompt in the GGUF template
CAVEATS
·RAM and VRAM estimates are conservative local-inference estimates based on GGUF file size plus runtime and KV-cache overhead, not official Mistral requirements.
·The fetched GGUF model card states the prompt format does not support a separate system prompt.
·The fetched sources did not provide a verified exhaustive language list, so languages is empty.
SOURCE URLS
FIELD EVIDENCE
contextWindowTokenshuggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.3-llamafile
supportsToolshuggingface.co/mistralai/Mistral-7B-Instruct-v0.3
parameterSizeBhuggingface.co/mistralai/Mistral-7B-Instruct-v0.3
CAPABILITIES
tool calling