Can I run Qwen3 14B on the GeForce RTX 3090?
Runs greatQ4_K_M fits in VRAM with 12.5 GB to spare: Runs great, est. 63.4 tok/s (55.7–71.0, calibrated estimate ±12%).
24 GB VRAM · 936.0 GB/s · FP16 35.6 TFLOPS. Assumes 32 GB of DDR5-5600 system RAM, Windows with this GPU driving the display, 8k context and an f16 KV cache.
Every quant of Qwen3 14B on the GeForce RTX 3090
| Quant | File size | Verdict | Speed | Memory | Runs as | Notes |
|---|---|---|---|---|---|---|
| Q2_K | 5.75 GB | Runs great | est. 92.4 tok/s81.3–103.5calibrated estimate ±12% | 8.3 / 24.0 GB | Full GPU | — |
| IQ4_XS | 8.14 GB | Runs great | est. 69.1 tok/s60.8–77.4calibrated estimate ±12% | 10.7 / 24.0 GB | Full GPU | — |
| Q4_K_Mbaseline | 9.00 GB | Runs great | est. 63.4 tok/s55.7–71.0calibrated estimate ±12% | 11.5 / 24.0 GB | Full GPU | — |
| Q8_0 | 15.70 GB | Runs great | est. 38.4 tok/s33.8–43.1calibrated estimate ±12% | 18.2 / 24.0 GB | Full GPU | — |
Where the memory goes at Q4_K_M
- Weights
- 9.0 GB
- KV cache
- 1.3 GB
- Compute buffer
- 0.6 GB
- OS reserve
- 0.6 GB
- Free
- 12.5 GB
Context length vs. KV cache
| Context | KV f16 | KV q8_0 | KV q4_0 |
|---|---|---|---|
| 4k | 10.2 GBRuns great est. 67.7 tok/s59.6–75.9calibrated estimate ±12% | 9.9 GBRuns great est. 70.0 tok/s61.6–78.4calibrated estimate ±12% | 9.7 GBRuns great est. 71.3 tok/s62.7–79.8calibrated estimate ±12% |
| 8k | 10.9 GBRuns great est. 63.4 tok/s55.7–71.0calibrated estimate ±12% | 10.3 GBRuns great est. 67.4 tok/s59.3–75.5calibrated estimate ±12% | 10.0 GBRuns great est. 69.8 tok/s61.5–78.2calibrated estimate ±12% |
| 16k | 12.3 GBRuns great est. 56.1 tok/s49.3–62.8calibrated estimate ±12% | 11.1 GBRuns great est. 62.8 tok/s55.2–70.3calibrated estimate ±12% | 10.4 GBRuns great est. 67.1 tok/s59.0–75.1calibrated estimate ±12% |
| 32k | 15.2 GBRuns great est. 45.6 tok/s40.1–51.1calibrated estimate ±12% | 12.7 GBRuns great est. 55.2 tok/s48.6–61.8calibrated estimate ±12% | 11.3 GBRuns great est. 62.2 tok/s54.8–69.7calibrated estimate ±12% |
S = Runs great · A = Runs well · B = Runs slowly · F = Won't run
At Q4_K_M the verdict stays Runs great up to 32k context with an f16 KV cache, and up to 32k with q8_0.
Estimated speed
- Generation
- est. 63.4 tok/s (55.7–71.0, calibrated estimate ±12%)
- Prompt processing
- about 4,984 tok/s (2,990–6,978, rough estimate ±40%)
Measured on this exact combination
No public measurement for this exact combination yet; the numbers above are estimates.
If this is not enough
A larger model that also runs well on the GeForce RTX 3090
Runs greatQwen3.5 35B-A3B: Runs great, est. 204.8 tok/s (163.9–245.8, calibrated estimate ±20%)
A larger quant that still runs great
Runs greatQ8_0 (15.70 GB): Runs great, est. 38.4 tok/s (33.8–43.1, calibrated estimate ±12%)
How to run it
Commands for the Q4_K_M file. Both tools download from Hugging Face on first run.
File: Qwen3-14B-Q4_K_M.gguf (9.00 GB) from unsloth/Qwen3-14B-GGUF.
llama-server -hf unsloth/Qwen3-14B-GGUF:Q4_K_M -c 8192 -ngl all -fa on- -ngl all loads every layer on the GPU.
- -fa on enables flash attention (needed for KV cache quantization).
- --cache-type-k q8_0 --cache-type-v q8_0 shrinks the KV cache to 0.72 GB at 8k context.
PowerShell (quit the Ollama tray app first):
$env:OLLAMA_CONTEXT_LENGTH="8192"; ollama serve
ollama run hf.co/unsloth/Qwen3-14B-GGUF:Q4_K_M- Ollama defaults to 4k context on GPUs under 24 GB. Set OLLAMA_CONTEXT_LENGTH when starting the server, or /set parameter num_ctx inside the chat.
/set parameter num_ctx 8192
Related pages
Guide: How much VRAM do local LLMs need? 8–32 GB tiers (2026)
Other models on the GeForce RTX 3090
Qwen3 14B on other hardware
Frequently asked questions
Can I run Qwen3 14B on the GeForce RTX 3090?
Q4_K_M fits in VRAM with 12.5 GB to spare: Runs great, est. 63.4 tok/s (55.7–71.0, calibrated estimate ±12%). Q4_K_M needs 10.9 GB at 8k context; this setup has 23.4 GB of usable memory and 28.0 GB of free system RAM.
How much context can Qwen3 14B use on the GeForce RTX 3090?
At Q4_K_M the verdict stays Runs great up to 32k context with an f16 KV cache (5.4 GB of KV) and up to 32k with a q8_0 KV cache (2.9 GB). The model supports up to 32k.
Which quant should I use, and how fast is it?
Q4_K_M (9.00 GB) is the recommended balance: Runs great, est. 63.4 tok/s (55.7–71.0, calibrated estimate ±12%). The largest tracked file that still gets Runs great is Q8_0 (15.70 GB), est. 38.4 tok/s (33.8–43.1, calibrated estimate ±12%).
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.