Can RTX 4090 24GB run Gemma 4 12B?
Measured results for Gemma 4 12B (11.96B dense) on RTX 4090 24GB, plus what fits and the commands to run it.
Short answer
Yes. Gemma 4 12B Q8_0 fits fully on RTX 4090 24GB at 16k context, using 13.3 of 23.0 GB usable, and generates about 64.2 tokens/s in our own run. As the context fills it slows down: 61.2 tok/s with 16k tokens already in context (95% of the empty-context speed), measured. For Q8_0, our bandwidth-only estimate was ~44 tok/s against a measured median of ~64 (32% too pessimistic).
Measured generation speed by quantization
| Quant | Generation tok/s | Range | Prompt tok/s | Runs | Origin |
|---|---|---|---|---|---|
| Q4 class (median) | 102 | 102–102 | 6465 | 1 | includes our runs |
| Q8 class (median) | 64.2 | 64.2–64.2 | 6420 | 1 | includes our runs |
| Q4_K_M (our run, depth 0) | 102 | 3 repeats | 6465 | 3 | own measurement |
| Q8_0 (our run, depth 0) | 64.2 | 3 repeats | 6420 | 3 | own measurement |
Generation = tg128 (128 generated tokens, short context). Public rows are medians of community llama.cpp results (sources); our own runs use llama-bench b11658 on a rented GPU.
Speed vs context depth measured
Our own llama-bench runs on GeForce RTX 4090 (flash attention on, 3 repeats): generation and prompt speed with the given number of tokens already in the context.
| Quant | Context depth | Generation tok/s | vs depth 0 | Prompt tok/s |
|---|---|---|---|---|
| Q4_K_M | 0 | 102 | 100% | 6465 |
| Q4_K_M | 4k | 97.8 | 96% | 6357 |
| Q4_K_M | 16k | 94.7 | 93% | 5290 |
| Q4_K_M | 32k | 92.9 | 91% | 4507 |
| Q4_K_M | 64k | 87.6 | 86% | 3359 |
| Q4_K_M | 128k | 79 | 77% | 2240 |
| Q8_0 | 0 | 64.2 | 100% | 6420 |
| Q8_0 | 4k | 62.5 | 97% | 6535 |
| Q8_0 | 16k | 61.2 | 95% | 5370 |
Alternatives
Less memory that still fits Gemma 4 12B
Smaller memory usually means a cheaper card or Mac (we do not list prices).
- Mac mini / iMac M4 16GB: Q4_K_M, 11 GB usable, ~11 tok/s scaled from measured
- RTX 5070 12GB: Q6_K, 11 GB usable, ~51 tok/s scaled from measured
- RTX 4070 12GB: Q6_K, 11 GB usable, ~43 tok/s scaled from measured
Faster for Gemma 4 12B
- RTX 5090 32GB: Q8_0, 31 GB usable, ~104 tok/s measured
- RTX PRO 6000 96GB: Q8_0, 95 GB usable, ~101 tok/s measured
Other models on RTX 4090 24GB, similar size
- Qwen3.5 9B: Q8_0, fits fully, ~95 tok/s (measured)
- Ornith 1.5 9B (hardware page): Q8_0, fits fully, ~95 tok/s (scaled from measured)
- Qwen3-VL 8B: Q8_0, fits fully, ~102 tok/s (measured)
- Gemma 4 E4B (hardware page): Q8_0, fits fully, ~96 tok/s (scaled from measured)
Memory and context limits
Q8_0 weights are 12.7 GB; the 16k f16 KV cache adds 0.60 GB. Largest context that fits in 23.0 GB usable:
| KV cache type | Max context |
|---|---|
| f16 | 256k |
| q8_0 | 256k |
| q4_0 | 256k |
Native limit 256k. Full KV cache table for Gemma 4 12B.
Copy-paste commands
The advisor's pick for this hardware: Q8_0, 16k context.
llama-server -hf unsloth/gemma-4-12b-it-GGUF:Q8_0 -c 16384 -fa on --jinja -ngl 99
OLLAMA_CONTEXT_LENGTH=16384 ollama serve ollama run hf.co/unsloth/gemma-4-12b-it-GGUF:Q8_0
FAQ
How fast is Gemma 4 12B on RTX 4090 24GB?
About 64.2 tokens/s for generation (Q8_0 on llama.cpp CUDA, 128-token generation), 6420 tokens/s for prompt processing. Speed drops as the context fills; see the depth table.
How much memory does Gemma 4 12B need on RTX 4090 24GB?
The advisor's pick, Q8_0, is 12.7 GB of weights plus 0.60 GB of KV cache at 16k context (13.3 GB), against 23.0 GB usable.
Is the Gemma 4 12B speed on RTX 4090 24GB measured or estimated?
Measured: our own llama-bench run on a rented GeForce RTX 4090, including runs with 4k to 128k tokens already in context.
What can I use instead of RTX 4090 24GB for Gemma 4 12B?
With less memory, Mac mini / iMac M4 16GB (~11 tok/s), RTX 5070 12GB (~51 tok/s), RTX 4070 12GB (~43 tok/s) also fit it fully. Faster: RTX 5090 32GB (~104 tok/s), RTX PRO 6000 96GB (~101 tok/s).
What is the maximum context for Gemma 4 12B on RTX 4090 24GB?
With an f16 KV cache about 256k tokens, 256k with q8_0 and 256k with q4_0, bounded by the model's own limit.
Related
All models on RTX 4090 24GB · Gemma 4 12B on all hardware · VRAM tier · all measured pages · leaderboard
Compare: RTX 3090 24GB vs RTX 4090 24GB · RTX 4090 24GB vs RTX 5090 32GB · RTX 4090 24GB vs AMD RX 7900 XTX 24GB · RTX 5080 16GB vs RTX 4090 24GB