Qwen 2 5 Coder 7b
Model size details
Family
Qwen
Open the family page when adjacent sizes change the decision.
Maker
Alibaba Qwen
Provider or project that owns the model lane.
Size
7B
Needs source review
VRAM
8 GB
Planning band for local quantized runs, not a benchmark guarantee.
Tasks
Chat, Code
Primary local jobs this row should help decide.
Context
128K
Context length affects VRAM and practical throughput.
Runtime path
Ollama, LM Studio, llama.cpp
Confirm current runtime and quant support before choosing a setup.
Quantization
Q4, Q8, GGUF
The available quant changes memory use, quality, and throughput.
Decision summary and limitation
A 7B text instruction model for local code generation, explanation, review, and fixing experiments.
Limitation: No performance, agent reliability, or memory-fit promise is verified; third-party GGUFs are not canonical evidence for this record.
Source, freshness and evidence
Primary source: official-huggingface-qwen
Freshness: Official model card and Apache-2.0 license checked 2026-08-06
Evidence: Official Qwen model card and license.
Family variants
Adjacent model sizes in the same family.
| Model | Tasks | VRAM | Fit band |
|---|---|---|---|
| Qwen 2 5 Coder 7b | Chat, Code | 8 GB | Fast local default |
| DeepSeek-R1-Distill-Qwen-7B | Chat, Reasoning | 8 GB | Fast local default |
| Qwen 3 14B | Chat | 16 GB | Device fit requires local validation |