Benchmark reports
999 reports · Newest first · Page 13 / 40
Qwen3-4B-Q8_0
Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q8_0.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q8_0 · llama.cpp
Qwen3-32B-Q4
Qwen/Qwen3-32B-GGUF/Qwen3-32B-Q4_K_M.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q4_K_M · llama.cpp
Qwen3-14B-Q4
Qwen/Qwen3-14B-GGUF/Qwen3-14B-Q4_K_M.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q4_K_M · llama.cpp
Qwen3-14B-AWQ
Qwen/Qwen3-14B-AWQ
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · AWQ · vLLM
Qwen3-8B-Q4
Qwen/Qwen3-8B-GGUF/Qwen3-8B-Q4_K_M.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q4_K_M · llama.cpp
Qwen3-4B-Q4
Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q4_K_M.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q4_K_M · llama.cpp
Qwen3-8B-AWQ
Qwen/Qwen3-8B-AWQ
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · AWQ · vLLM
Qwen3-1.7B-Q8
Qwen/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q8_0.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q8_0 · llama.cpp
qwen2.5-3b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-3B-Instruct-GGUF/qwen2.5-3b-instruct-q4_k_m.gguf
T4 · 16 GB
Text generation · Q4_K_M · llama.cpp
Qwen3-0.6B-Q8
Qwen/Qwen3-0.6B-GGUF/Qwen3-0.6B-Q8_0.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q8_0 · llama.cpp
qwen2.5-3b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-3B-Instruct-GGUF/qwen2.5-3b-instruct-q4_k_m.gguf
A100-SXM4-40GB · 40 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-3b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-3B-Instruct-GGUF/qwen2.5-3b-instruct-q4_k_m.gguf
L4 · 24 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-3b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-3B-Instruct-GGUF/qwen2.5-3b-instruct-q4_k_m.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-1.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-1.5B-Instruct-GGUF/qwen2.5-1.5b-instruct-q4_k_m.gguf
T4 · 16 GB
Text generation · Q4_K_M · llama.cpp
Qwen3-4B-AWQ
Qwen/Qwen3-4B-AWQ
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · AWQ · vLLM
qwen2.5-1.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-1.5B-Instruct-GGUF/qwen2.5-1.5b-instruct-q4_k_m.gguf
A100-SXM4-40GB · 40 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-1.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-1.5B-Instruct-GGUF/qwen2.5-1.5b-instruct-q4_k_m.gguf
L4 · 24 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-1.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-1.5B-Instruct-GGUF/qwen2.5-1.5b-instruct-q4_k_m.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-0.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-0.5B-Instruct-GGUF/qwen2.5-0.5b-instruct-q4_k_m.gguf
T4 · 16 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-0.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-0.5B-Instruct-GGUF/qwen2.5-0.5b-instruct-q4_k_m.gguf
A100-SXM4-40GB · 40 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-0.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-0.5B-Instruct-GGUF/qwen2.5-0.5b-instruct-q4_k_m.gguf
L4 · 24 GB
Text generation · Q4_K_M · llama.cpp
qwen2.5-0.5b-instruct-q4_k_m.gguf
Qwen/Qwen2.5-0.5B-Instruct-GGUF/qwen2.5-0.5b-instruct-q4_k_m.gguf
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · Q4_K_M · llama.cpp
Qwen3-4B
/content/wbench-formal-20261014/job-010/cache/huggingface/models--Qwen--Qwen3-4B/snapshots/1cfa9a7208912126459214e8b04321603b3df60c
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · BF16 · vLLM
Qwen3-1.7B
/content/wbench-formal-20261014/job-009/cache/huggingface/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · BF16 · vLLM
DeepSeek-R1-Distill-Qwen-1.5B
/content/wbench-formal-20261014/job-008/cache/huggingface/models--deepseek-ai--DeepSeek-R1-Distill-Qwen-1.5B/snapshots/ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562
RTX PRO 6000 Blackwell Server Edition · 96 GB
Text generation · BF16 · vLLM
Updated