RX 9070 XT 16GB

49 models / sorted by best_quality

Quality Fastest Least mem Newest
Runs comfortably
Qwen3.8-27B UD-Q2_K_XL Unsloth
9.8GB 262k ctx
FIT Runs comfortably
SPEED 36 tok/s
ⓘ estimated
MEMORY 10/16GB
Qwen3.8-27B UD-IQ1_S Unsloth
6.2GB 262k ctx
FIT Runs comfortably
SPEED 57 tok/s
ⓘ estimated
MEMORY 6/16GB
Ornith-1.5-9B Q8_0
9.8GB 262k ctx
FIT Runs comfortably
SPEED 36 tok/s
ⓘ estimated
MEMORY 10/16GB
Ornith-1.5-9B Q6_K
7.6GB 262k ctx
FIT Runs comfortably
SPEED 47 tok/s
ⓘ estimated
MEMORY 8/16GB
Ornith-1.5-9B Q5_K_M
6.6GB 262k ctx
FIT Runs comfortably
SPEED 53 tok/s
ⓘ estimated
MEMORY 7/16GB
Ornith-1.5-9B Q4_K_M
5.8GB 262k ctx
FIT Runs comfortably
SPEED 61 tok/s
ⓘ estimated
MEMORY 6/16GB
Phi-4 14B Q4_K_M
8.5GB 16k ctx
FIT Runs comfortably
SPEED 41 tok/s
ⓘ estimated
MEMORY 9/16GB
Qwen3 14B Q4_K_M
9.0GB 128k ctx
FIT Runs comfortably
SPEED 39 tok/s
ⓘ estimated
MEMORY 9/16GB
Gemma 4 12B Q8_0
13.0GB 128k ctx
FIT Runs comfortably
SPEED 27 tok/s
ⓘ estimated
MEMORY 13/16GB
Gemma 4 12B Q4_K_M
7.2GB 128k ctx
FIT Runs comfortably
SPEED 49 tok/s
ⓘ estimated
MEMORY 7/16GB
Qwen3 8B Q4_K_M
5.2GB 128k ctx
FIT Runs comfortably
SPEED 68 tok/s
ⓘ estimated
MEMORY 5/16GB
Qwen3 8B Q8_0
8.5GB 128k ctx
FIT Runs comfortably
SPEED 41 tok/s
ⓘ estimated
MEMORY 9/16GB
Gemma 3 12B Q8_0
13.5GB 128k ctx
FIT Runs comfortably
SPEED 26 tok/s
ⓘ estimated
MEMORY 14/16GB
Gemma 3 12B Q4_K_M
7.5GB 128k ctx
FIT Runs comfortably
SPEED 47 tok/s
ⓘ estimated
MEMORY 8/16GB
Mistral Nemo 12B Q4_K_M
7.3GB 128k ctx
FIT Runs comfortably
SPEED 48 tok/s
ⓘ estimated
MEMORY 7/16GB
Mistral Nemo 12B Q8_0
13.2GB 128k ctx
FIT Runs comfortably
SPEED 27 tok/s
ⓘ estimated
MEMORY 13/16GB
Qwen3 4B Q4_K_M
2.6GB 32k ctx
FIT Runs comfortably
SPEED 135 tok/s
ⓘ estimated
MEMORY 3/16GB
Phi-4 Mini Q8_0
4.1GB 128k ctx
FIT Runs comfortably
SPEED 86 tok/s
ⓘ estimated
MEMORY 4/16GB
Phi-4 Mini Q4_K_M
2.5GB 128k ctx
FIT Runs comfortably
SPEED 141 tok/s
ⓘ estimated
MEMORY 3/16GB
Llama 3.1 8B Instruct Q8_0
8.0GB 128k ctx
FIT Runs comfortably
SPEED 44 tok/s
ⓘ estimated
MEMORY 8/16GB
Llama 3.1 8B Instruct Q4_K_M
4.5GB 128k ctx
FIT Runs comfortably
SPEED 78 tok/s
ⓘ estimated
MEMORY 5/16GB
Gemma 3 4B Q8_0
5.0GB 128k ctx
FIT Runs comfortably
SPEED 70 tok/s
ⓘ estimated
MEMORY 5/16GB
Gemma 3 4B Q4_K_M
3.0GB 128k ctx
FIT Runs comfortably
SPEED 117 tok/s
ⓘ estimated
MEMORY 3/16GB
Llama 3.2 3B Instruct Q8_0
3.5GB 128k ctx
FIT Runs comfortably
SPEED 101 tok/s
ⓘ estimated
MEMORY 4/16GB
Llama 3.2 3B Instruct Q4_K_M
2.0GB 128k ctx
FIT Runs comfortably
SPEED 176 tok/s
ⓘ estimated
MEMORY 2/16GB
Runs tight
Gemma 4 26B A4B Q4_K_M
13.0GB 0k cap
FIT Runs tight
SPEED 179 tok/s
ⓘ estimated
MEMORY 13/16GB
Qwen3 30B A3B Q4_K_M
15.5GB 128k ctx
FIT Runs tight
SPEED 231 tok/s
ⓘ estimated
MEMORY 16/16GB
Phi-4 14B Q8_0
15.0GB 16k ctx
FIT Runs tight
SPEED 23 tok/s
ⓘ estimated
MEMORY 15/16GB
Qwen3 14B Q8_0
15.0GB 128k ctx
FIT Runs tight
SPEED 23 tok/s
ⓘ estimated
MEMORY 15/16GB
Llama 3.1 8B Instruct FP16
16.0GB 0k cap
FIT Runs tight
SPEED 22 tok/s
ⓘ estimated
MEMORY 16/16GB
Runs with CPU offload
Qwen3.8-Flash-Next EXL3_2BPW
62.7GB 0k cap
FIT Runs with CPU offload
SPEED 168 tok/s
ⓘ estimated
MEMORY 63/16GB
Qwen3.8-Flash-Next EXL3_3BPW
85.0GB 0k cap
FIT Runs with CPU offload
SPEED 124 tok/s
ⓘ estimated
MEMORY 85/16GB
Ornith-1.5-35B-A3B Q5_K_M
25.3GB 0k cap
FIT Runs with CPU offload
SPEED 167 tok/s
ⓘ estimated
MEMORY 25/16GB
Ornith-1.5-35B-A3B Q4_K_M
21.7GB 0k cap
FIT Runs with CPU offload
SPEED 194 tok/s
ⓘ estimated
MEMORY 22/16GB
Qwen3.6 35B A3B Q4_K_M
20.0GB 0k cap
FIT Runs with CPU offload
SPEED 205 tok/s
ⓘ estimated
MEMORY 20/16GB
Pokee-Isaac 28B Q4_K_M
16.0GB 0k cap
FIT Runs with CPU offload
SPEED 22 tok/s
ⓘ estimated
MEMORY 16/16GB
Qwen3.8-27B UD-Q4_K_XL Unsloth
17.6GB 0k cap
FIT Runs with CPU offload
SPEED 20 tok/s
ⓘ estimated
MEMORY 18/16GB
Gemma 4 31B Q4_K_M
18.3GB 0k cap
FIT Runs with CPU offload
SPEED 19 tok/s
ⓘ estimated
MEMORY 18/16GB
Gemma 4 31B QAT
18.0GB 0k cap
FIT Runs with CPU offload
SPEED 20 tok/s
ⓘ estimated
MEMORY 18/16GB
Qwen3.6 27B Q4_K_M
16.5GB 0k cap
FIT Runs with CPU offload
SPEED 21 tok/s
ⓘ estimated
MEMORY 17/16GB
Qwen3 32B Q5_K_M
24.5GB 0k cap
FIT Runs with CPU offload
SPEED 14 tok/s
ⓘ estimated
MEMORY 25/16GB
Qwen3 32B Q4_K_M
20.0GB 0k cap
FIT Runs with CPU offload
SPEED 18 tok/s
ⓘ estimated
MEMORY 20/16GB
Ornith-1.5-9B BF16
18.4GB 0k cap
FIT Runs with CPU offload
SPEED 19 tok/s
ⓘ estimated
MEMORY 18/16GB
Xing4.0-29B-A4B Q4_K_M
20.1GB 256k ctx
FIT Runs with CPU offload
SPEED 127 tok/s
ⓘ estimated
MEMORY 20/16GB
Llama 3.3 70B Instruct Q2_K
21.5GB 0k cap
FIT Runs with CPU offload
SPEED 16 tok/s
ⓘ estimated
MEMORY 22/16GB
Gemma 3 27B Q4_K_M
17.0GB 0k cap
FIT Runs with CPU offload
SPEED 21 tok/s
ⓘ estimated
MEMORY 17/16GB
Mixtral 8x7B Instruct Q4_K_M
26.5GB 0k cap
FIT Runs with CPU offload
SPEED 48 tok/s
ⓘ estimated
MEMORY 27/16GB
Mixtral 8x7B Instruct Q3_K_M
19.0GB 0k cap
FIT Runs with CPU offload
SPEED 67 tok/s
ⓘ estimated
MEMORY 19/16GB
Muse Glimmer 30B Q4_K_M
18.0GB 0k cap
FIT Runs with CPU offload
SPEED 20 tok/s
ⓘ estimated
MEMORY 18/16GB

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