Skip to content

RTX 4060 8GB

25 models / sorted by best_quality

Quality Fastest Least mem Newest
Runs comfortably
Ornith-1.5-9B Q4_K_M
5.8GB 4k cap
FIT Runs comfortably
SPEED 19 tok/s
ⓘ estimated
MEMORY 6/8GB
Qwen3 8B Q4_K_M
5.2GB 5k cap
FIT Runs comfortably
SPEED 21 tok/s
ⓘ estimated
MEMORY 5/8GB
Qwen3 4B Q4_K_M
2.6GB 19k cap
FIT Runs comfortably
SPEED 40 tok/s
ⓘ estimated
MEMORY 3/8GB
Phi-4 Mini Q4_K_M
2.5GB 27k cap
FIT Runs comfortably
SPEED 45 tok/s
ⓘ estimated
MEMORY 3/8GB
Phi-4 Mini Q8_0
4.1GB 19k cap
FIT Runs comfortably
SPEED 30 tok/s
ⓘ estimated
MEMORY 4/8GB
Llama 3.1 8B Instruct Q4_K_M
4.5GB 7k cap
FIT Runs comfortably
SPEED 23 tok/s
ⓘ estimated
MEMORY 5/8GB
Gemma 3 4B Q4_K_M
3.0GB 16k cap
FIT Runs comfortably
SPEED 35 tok/s
ⓘ estimated
MEMORY 3/8GB
Gemma 3 4B Q8_0
5.0GB 10k cap
FIT Runs comfortably
SPEED 24 tok/s
ⓘ estimated
MEMORY 5/8GB
Llama 3.2 3B Instruct Q4_K_M
2.0GB 24k cap
FIT Runs comfortably
SPEED 50 tok/s
ⓘ estimated
MEMORY 2/8GB
Llama 3.2 3B Instruct Q8_0
3.5GB 18k cap
FIT Runs comfortably
SPEED 33 tok/s
ⓘ estimated
MEMORY 4/8GB
Runs tight
Qwen3.8-27B UD-IQ1_S Unsloth
6.2GB ctx headroom ~0
FIT Runs tight
SPEED 18 tok/s
ⓘ estimated
MEMORY 6/8GB
Ornith-1.5-9B Q6_K
7.6GB ctx headroom ~0
FIT Runs tight
SPEED 16 tok/s
ⓘ estimated
MEMORY 8/8GB
Ornith-1.5-9B Q5_K_M
6.6GB 2k cap
FIT Runs tight
SPEED 17 tok/s
ⓘ estimated
MEMORY 7/8GB
Gemma 4 12B Q4_K_M
7.2GB 1k cap
FIT Runs tight
SPEED 17 tok/s
ⓘ estimated
MEMORY 7/8GB
Gemma 3 12B Q4_K_M
7.5GB 1k cap
FIT Runs tight
SPEED 16 tok/s
ⓘ estimated
MEMORY 8/8GB
Mistral Nemo 12B Q4_K_M
7.3GB 1k cap
FIT Runs tight
SPEED 17 tok/s
ⓘ estimated
MEMORY 7/8GB
Llama 3.1 8B Instruct Q8_0
8.0GB ctx headroom ~0
FIT Runs tight
SPEED 15 tok/s
ⓘ estimated
MEMORY 8/8GB
Runs with CPU offload
Qwen3.8-27B UD-Q2_K_XL Unsloth
9.8GB ctx spills to ram
FIT Runs with CPU offload
SPEED 5 tok/s
ⓘ estimated
MEMORY 10/8GB
Ornith-1.5-9B Q8_0
9.8GB ctx spills to ram
FIT Runs with CPU offload
SPEED 6 tok/s
ⓘ estimated
MEMORY 10/8GB
Phi-4 14B Q4_K_M
8.5GB ctx spills to ram
FIT Runs with CPU offload
SPEED 9 tok/s
ⓘ estimated
MEMORY 9/8GB
Qwen3 14B Q4_K_M
9.0GB ctx spills to ram
FIT Runs with CPU offload
SPEED 8 tok/s
ⓘ estimated
MEMORY 9/8GB
Gemma 4 12B Q8_0
13.0GB ctx spills to ram
FIT Runs with CPU offload
SPEED 4 tok/s
ⓘ estimated
MEMORY 13/8GB
Qwen3 8B Q8_0
8.5GB ctx spills to ram
FIT Runs with CPU offload
SPEED 9 tok/s
ⓘ estimated
MEMORY 9/8GB
Mistral Nemo 12B Q8_0
13.2GB ctx spills to ram
FIT Runs with CPU offload
SPEED 4 tok/s
ⓘ estimated
MEMORY 13/8GB
Mellum2.1 12B Thinking Q4_K_M
7.0GB ctx spills to ram
FIT Runs with CPU offload
SPEED 1 tok/s
ⓘ estimated
MEMORY 7/8GB

Coding alternatives

Hosted coding assistants for comparison - per seat

Cursor Hobby
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$0.0
/MONTH
GitHub Copilot Individual
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$10.0
/MONTH
GitHub Copilot Business
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$19.0
/MONTH
Cursor Pro
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$20.0
/MONTH
GitHub Copilot Enterprise
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$39.0
/MONTH
Cursor Business
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$40.0
/MONTH

Per-token monthly figures are estimates at typical usage. Prices verified periodically - always confirm current pricing on the provider's website.

On a monthly budget? Compare owning hardware vs renting cloud →

Sign in with GitHub to save this rig and get weekly model updates

Sign in with GitHub

Tokenstead community

Not sure this is the right fit?

Post your rig and the shortlist in the community and get a sanity check from people running the same memory and stack.

Join the community Share your rig