Skip to content

Typhoon2.5 Qwen3 4B on RTX 4060: VRAM, speed and fit

Typhoon2.5 Qwen3 4B at 8-bit runs on the RTX 4060 with 16K of context at about 43 tokens a second.

Text generation · Chat · Ollama / LM Studio

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

GPU memory
7.0 GB
of 8.0 GB
Context
16K
auto
Speed
43 tok/s
28 when full
First reply
0.5 s
2K prompt

Where the memory goes

Model
4.0 GB
Context
2.3 GB
Overhead
838 MB
OS
0.0 GB
Free
1.0 GB
Memory
7.0 GB of 8.0 GB
Context
16K tokens · auto
Speed
43 tok/s · 28 when full
First reply
0.5 s for a 2K prompt
Running cost
$3.26/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated

What Typhoon2.5 Qwen3 4B on RTX 4060 was checked against
CheckTargetResultStatus
Fits in GPU memory8.0 GB usable7.0 GB neededPass
Headroom5% free1.0 GB free (12%)Pass
Context for chat16K or more16KPass
Writing speed15 tok/s or more43 tok/sPass
First replyunder 3 s, 2K prompt0.5 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
Typhoon2.5 Qwen3 4B
Parameters
4B
Precision
8-bit (Q8_0)
Context
16K, 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 36K 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

llama.cpp
llama-server -hf typhoon-ai/typhoon2.5-qwen3-4b-gguf
vLLM
vllm serve typhoon-ai/typhoon2.5-qwen3-4b

Typhoon2.5 Qwen3 4B on similar machines

All machines: Typhoon2.5 Qwen3 4B VRAM requirements. Everything that runs here: what can the RTX 4060 run?

Other models that run on RTX 4060

Questions

Can Typhoon2.5 Qwen3 4B run on RTX 4060?

Typhoon2.5 Qwen3 4B at 8-bit runs on the RTX 4060 with 16K of context at about 43 tokens a second.

Report VR-0TTVOUN, calculated Nov 22, 2026 from published specs, not benchmarked.