Skip to content

Qwen3.5 4B on RTX 4060: VRAM, speed and fit

Qwen3.5 4B at 8-bit runs on the RTX 4060 with 60K of context at about 37 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 4060 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
7.5 GB
of 8.0 GB
Context
60K
auto
Speed
37 tok/s
26 when full
First reply
0.6 s
2K prompt

Where the memory goes

Model
4.6 GB
Context
1.9 GB
Overhead
1.0 GB
OS
0.0 GB
Free
475 MB
Memory
7.5 GB of 8.0 GB
Context
60K tokens · auto
Speed
37 tok/s · 26 when full
First reply
0.6 s for a 2K prompt
Running cost
$3.26/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What Qwen3.5 4B on RTX 4060 was checked against
CheckTargetResultStatus
Fits in GPU memory8.0 GB usable7.5 GB neededPass
Headroom5% free475 MB free (6%)Pass
Context for chat16K or more60KPass
Writing speed15 tok/s or more37 tok/sPass
First replyunder 3 s, 2K prompt0.6 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Qwen3.5 4B
Parameters
4.7B
Precision
8-bit (Q8_0)
Context
60K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 4060
GPU can use
8.0 GB of 8.0 GB

Worth trying

  • 8-bit cache: Room for 112K context

Running cost

At home
$3.26/mo
149 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

Ollama
ollama run qwen3.5:4b
llama.cpp
llama-server -hf unsloth/Qwen3.5-4B-GGUF
vLLM
vllm serve Qwen/Qwen3.5-4B
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3.5-4B-MLX-4bit

Qwen3.5 4B on similar machines

All machines: Qwen3.5 4B VRAM requirements. Everything that runs here: what can the RTX 4060 run?

Other models that run on RTX 4060

Questions

Can Qwen3.5 4B run on RTX 4060?

Qwen3.5 4B at 8-bit runs on the RTX 4060 with 60K of context at about 37 tokens a second.

Report VR-04KBNEL, calculated Nov 22, 2026 from published specs, not benchmarked.