Qwen2.5 14B Instruct
Alibaba Qwen
The sweet spot for 24 GB cards. Meaningfully stronger reasoning than 7B while still fine-tunable locally with QLoRA.
Runs with CPU offload
- Weights
- 8.3 GB
- KV cache
- 1.5 GB
- Overhead
- 720 MB
- 11 GB of 11 GB usable VRAM.
- Chosen as the best quality that still fits a 4,096-token context (9.8 GB at that length).
- Best all-round fit for a 24 GB GPU
- Holds long instructions well
- Apache 2.0
- Needs quantization below 24 GB
- Slower than 7B for interactive use
qwen2.5:14bRunning Qwen2.5 14B Instruct on GeForce RTX 4070
| Quantization | Quality | Weights | KV cache | Total | ~tok/s | Fit |
|---|---|---|---|---|---|---|
| F16 | lossless | 28 GB | 1.5 GB | 30 GB | 13 | Runs with CPU offload |
| Q8_0 | near-lossless | 15 GB | 1.5 GB | 17 GB | 25 | Runs with CPU offload |
| Q6_K | near-lossless | 11 GB | 1.5 GB | 14 GB | 32 | Runs with CPU offload |
| Q5_K_M | high | 9.8 GB | 1.5 GB | 12 GB | 37 | Runs with CPU offload |
| Q4_K_MPick | balanced | 8.3 GB | 1.5 GB | 11 GB | 44 | Runs with CPU offload |
| Q3_K_M | degraded | 6.7 GB | 1.5 GB | 9.0 GB | 54 | Tight fit |
KV cache is sized at 8,192 tokens. Longer contexts cost proportionally more — the recommendation above reserves room for a working context.
Local fine-tuning on this machine
- Base weights
- 7.8 GB
- Optimizer
- 1.0 GB
- Activations
- 1.3 GB
- Peak
- 12 GB
- QLoRA still needs 12 GB; this machine has 11 GB. Choose a smaller base model.
- Base weights
- 28 GB
- Optimizer
- 1.0 GB
- Activations
- 1.3 GB
- Peak
- 32 GB
- Needs 32 GB — switch to QLoRA to cut the weight footprint.
Where this model runs
VRAM 32 GB · Q8_0 · 17 GB
VRAM 24 GB · Q6_K · 14 GB
VRAM 16 GB · Q5_K_M · 12 GB
VRAM 16 GB · Q5_K_M · 12 GB
VRAM 24 GB · Q6_K · 14 GB
VRAM 12 GB · Q4_K_M · 11 GB
VRAM 12 GB · Q4_K_M · 11 GB
VRAM 16 GB · Q5_K_M · 12 GB
VRAM 48 GB · F16 · 30 GB
VRAM 80 GB · F16 · 30 GB
Unified 128 GB · F16 · 30 GB
Unified 48 GB · Q8_0 · 17 GB
Unified 24 GB · Q5_K_M · 12 GB
Unified 192 GB · F16 · 30 GB
Unified 16 GB · Q4_K_M · 11 GB
VRAM 24 GB · Q6_K · 14 GB
VRAM 16 GB · Q5_K_M · 12 GB
VRAM 0 MB
VRAM 0 MB
79.7%
Qwen2.5 model card
83.5%
Qwen2.5 model card
Reported by the model's author. ModelLM has not run these benchmarks and does not treat them as verified.
Qwen2.5 7B Instruct
7.6B · Apache 2.0
The default starting point for local work on 8–12 GB cards. Strong instruction following and reliable tool-call formatting for its size.
Qwen2.5 32B Instruct
32.8B · Apache 2.0
Approaches 70B quality at half the memory. Runs on a single 24 GB card at Q4_K_M with a modest context window.
Qwen2.5 72B Instruct
72.7B · Qwen License
Frontier-adjacent open weights. Needs a workstation, a multi-GPU rig or a large unified-memory Mac.
Qwen2.5 Coder 7B Instruct
7.6B · Apache 2.0
The practical local copilot. Supports fill-in-the-middle, so it works as an inline completion model rather than only a chat assistant.
Catalogue figures come from each model’s published card. ModelLM has not independently measured them.