Gemma 2 9B Instruct
Unusually good at natural, well-structured prose for its size. The short context is the catch.
Excellent fit
- Weights
- 9.1 GB
- KV cache
- 2.3 GB
- Overhead
- 620 MB
- 12 GB of 23 GB usable VRAM.
- Chosen as the best quality that still fits a 8,192-token context (12 GB at that length).
- Excellent writing quality
- Strong instruction following
- Large multilingual vocabulary
- 8k context only
- Large vocabulary inflates the embedding layer
- Weak at code
gemma2:9bRunning Gemma 2 9B Instruct on GeForce RTX 4090
| Quantization | Quality | Weights | KV cache | Total | ~tok/s | Fit |
|---|---|---|---|---|---|---|
| F16 | lossless | 17 GB | 2.3 GB | 20 GB | 42 | Tight fit |
| Q8_0Pick | near-lossless | 9.1 GB | 2.3 GB | 12 GB | 80 | Excellent fit |
| Q6_K | near-lossless | 7.0 GB | 2.3 GB | 9.9 GB | 103 | Excellent fit |
| Q5_K_M | high | 6.1 GB | 2.3 GB | 9.0 GB | 120 | Excellent fit |
| Q4_K_M | balanced | 5.2 GB | 2.3 GB | 8.1 GB | 140 | Excellent fit |
| Q3_K_M | degraded | 4.2 GB | 2.3 GB | 7.1 GB | 173 | Excellent fit |
KV cache is sized at 8,192 tokens. Longer contexts cost proportionally more — the recommendation above reserves room for a working context.
You can fine-tune this here
- Base weights
- 4.8 GB
- Optimizer
- 790 MB
- Activations
- 960 MB
- Peak
- 8.2 GB
- 8.2 GB peak against 23 GB usable — room to raise batch size or sequence length.
- Base weights
- 17 GB
- Optimizer
- 790 MB
- Activations
- 960 MB
- Peak
- 21 GB
- Fits, but an OOM is likely if the sequence length or batch size rises.
Where this model runs
VRAM 32 GB · F16 · 20 GB
VRAM 24 GB · Q8_0 · 12 GB
VRAM 16 GB · Q6_K · 9.9 GB
VRAM 16 GB · Q6_K · 9.9 GB
VRAM 24 GB · Q8_0 · 12 GB
VRAM 12 GB · Q4_K_M · 8.1 GB
VRAM 12 GB · Q4_K_M · 8.1 GB
VRAM 16 GB · Q6_K · 9.9 GB
VRAM 48 GB · F16 · 20 GB
VRAM 80 GB · F16 · 20 GB
Unified 128 GB · F16 · 20 GB
Unified 48 GB · F16 · 20 GB
Unified 24 GB · Q8_0 · 12 GB
Unified 192 GB · F16 · 20 GB
Unified 16 GB · Q5_K_M · 9.0 GB
VRAM 24 GB · Q8_0 · 12 GB
VRAM 16 GB · Q6_K · 9.9 GB
VRAM 0 MB
VRAM 0 MB
71.3%
Gemma 2 technical report
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 14B Instruct
14.8B · Apache 2.0
The sweet spot for 24 GB cards. Meaningfully stronger reasoning than 7B while still fine-tunable locally with QLoRA.
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.
Qwen3 8B
8.2B · Apache 2.0
Switchable thinking mode: the same weights answer directly or reason step by step depending on the prompt. Long context for its size.
Catalogue figures come from each model’s published card. ModelLM has not independently measured them.