Lmstudio-community
Qwen3.5 9B (9B parameters) requires approximately 8.3 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Qwen3.5 9B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "lmstudio-community/Qwen3.5-9B-GGUF" \
--hf-file "Qwen3.5-9B-GGUF-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
Related models
Inference speed
Estimated decode speed (tokens/sec) for Qwen3.5 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~126 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 126.0 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 126.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 125.9 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 119.3 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 111.3 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 101.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 84.5 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 80.1 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 68.9 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 68.3 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 68.3 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 43.7 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 43.3 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 40.1 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 35.2 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 23.4 | Offloads |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quick picks
Best hardware
Run this model
Quantization
How much VRAM Qwen3.5 9B (9B) needs at each GGUF quant, and whether it fits a 24 GB card (RTX 4090 / 3090). The recommended Q4_K_M uses ~5.5 GB — about 43% less VRAM than Q8_0, at a small quality cost.
| Quant | Bits | VRAM (weights) | Quality | Fits 24 GB? |
|---|---|---|---|---|
| Q2_K | 2 | 3.5 GB | Low | Fits |
| Q3_K_S | 3 | 4.4 GB | Low | Fits |
| NVFP4 | 4 | 5 GB | Medium | Fits |
| Q4_K_Mrecommended | 4 | 5.5 GB | Medium | Fits |
| Q5_K_M | 5 | 6.5 GB | High | Fits |
| Q6_K | 6 | 7.4 GB | High | Fits |
| Q8_0 | 8 | 9.6 GB | Very High | Fits |
| F16 | 16 | 18.5 GB | Maximum | Offloads |
VRAM shown is quantized weights only; add ~1–3 GB runtime overhead plus KV cache for your context length. Lower quants trade quality for memory — Q4_K_M is the usual sweet spot; Q2/Q3 only when you must fit a bigger model.
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Qwen3.5 9B (9B parameters) requires approximately 8.3 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Intel Arc B570 10GB can run Qwen3.5 9B with a compatibility score of 51/100. It provides 10 GB of memory and achieves approximately 37.4 tokens per second.
The recommended quantization for Qwen3.5 9B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Qwen3.5 9B: RTX 3080 Ti 12GB (score: 57/100), RTX 3080 12GB (score: 57/100), RTX 5070 12GB (score: 57/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Qwen3.5 9B is well-suited for chat. It was designed with these use cases in mind.
See also
