v2.2 · 2026-06-12
Qwen2.5-Coder 7B Instruct
qwen2-5-coder-7b-instruct
Qwen2.5-Coder 7B Instruct is a 7.61B code 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
Qwen
FAMILY
Qwen2.5-Coder
MODEL TYPE
code
PARAMETERS
7.61B
MODALITIES
text
ARCHITECTURE
Decoder-only causal Transformer using Qwen2 architecture with RoPE, SwiGLU, RMSNorm, Attention QKV bias, and grouped-query attention; code-specific Qwen2.5-Coder post-training.
CONTEXT WINDOW
131,072 tokens
TRAINING TOKENS
5.5T
RELEASE DATE
2024-09-19
GGUF REPOSITORIES
Qwen/Qwen2.5-Coder-7B-Instruct-GGUF official
Official Qwen GGUF quantization repository; large variants may be split into multiple GGUF shards for a single quantization.
SETUP HINTS
OLLAMA
Use `ollama run qwen2.5-coder:7b` for Ollama's packaged build, or `ollama run hf.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF:Q4_K_M` to pin the official Hugging Face GGUF.LM STUDIO
Search for `Qwen/Qwen2.5-Coder-7B-Instruct-GGUF` in LM Studio and select Q4_K_M or Q5_K_M.
LLAMA.CPP
Use `llama-server -hf Qwen/Qwen2.5-Coder-7B-Instruct-GGUF:Q4_K_M`; for split GGUF downloads, download all shards for the chosen quantization and merge if your runtime requires a single file.QUANTIZATION FILE SIZES (GGUF)
Q4_K_M
4.68 GB
Q5_K_M
5.44 GB
Q8_0
8.1 GB
Quantization note: Q4_K_M for broad local compatibility; Q5_K_M for better code quality if memory allows.
RAM / VRAM ESTIMATES
MIN RAM
6.7 GB
COMFORTABLE RAM
9.4 GB
MIN VRAM
6.2 GB
COMFORTABLE VRAM
8.4 GB
These are conservative local-inference estimates, not official hardware requirements.
HARDWARE FIT
CPU only (no GPU)
yes
8 GB RAM
usable
16 GB RAM
good
32 GB RAM
good
8 GB VRAM
usable
12 GB VRAM
good
24 GB VRAM
good
Apple Silicon (unified memory)
good_16gb_plus
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
·Local coding assistant use on 16GB RAM machines.
·Code generation, code reasoning, and code repair at a small local footprint.
·CLI/editor helper experiments where a 32B code model is too heavy.
AVOID IF
·You need the strongest Qwen2.5-Coder checkpoint; use 32B if hardware permits.
·Your primary use is general creative chat rather than code.
·You only have 8GB RAM and need comfortable multitasking.
CAVEATS
·RAM and VRAM figures are estimates from GGUF file size plus conservative runtime and KV-cache overhead; exact memory depends on context length, batch size, backend, and GPU offload.
·Official Qwen2.5-Coder cards state long-context support up to 128K, but GGUF cards and local runtimes commonly default to 32K unless configured otherwise.
·Tool-use support was not treated as verified for this record because the official model card describes code-agent use cases but does not provide a specific tool-calling support field for this checkpoint.
SOURCE URLS
FIELD EVIDENCE
parameterSizeBhuggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct
architecturehuggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct
contextWindowTokenshuggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct
trainingTokenshuggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct
releaseDateqwenlm.github.io/blog/qwen2.5-coder/
languagesollama.com/library/qwen2.5-coder
LANGUAGES
40+ programming languages
CAPABILITIES
code tuned