AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

GLM-4.7-Flash on AMD GPUs

84 results · 7 sources · 135 measurements

Explore all results

Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed

Documented results

24 selected tests
View
ReportCustom evaluation		GLM-4.7-FlashQ4_K_MModel ref. ↗Conflicting evidenceHumanEval100 problems
90 %Reported pass@1 · n = 100
—
69.8 tok/sGeneration · mean · per request
2 × W7800Layer split · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Ubuntu 24.04 LTS
Engine
Ollama
Backend
ROCm
Harness
BoJl unified evaluation harness (2026-08)
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashQ4_K_MModel ref. ↗Token speed—
264.4 tok/sPrefill · unknown
21.5 tok/sGeneration · unknown
1 × RX 7700 XTSingle GPU · 12 GB VRAM/GPU
Configuration
Memory
12 GB VRAM/GPU
OS
Windows 11
Engine
vllm
Backend
Not reported
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
27 / 1024 tokens
Context
2048
Concurrency
Not reported
Date
2026-07-16
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashMXFP4_MOEModel ref. ↗Token speed—
2,085.45 tok/sPrefill · unknown
97.39 tok/sGeneration · peak · unknown
3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Arch Linux
Engine
llama.cpp
Backend
vulkan
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
527 / 256 tokens
Context
783
Concurrency
Not reported
Date
2026-08-04
Full record →
View
Reportllama-bench		GLM-4.7-FlashBF16Model ref. ↗Token speed512 input tokens · 0 output tokens · 0 existing KV tokens—
422.28 tok/sPrefill · mean · per request
—1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Fedora Linux 43 (Workstation Edition)
Engine
llama.cpp
Backend
ROCm / rocm-7_2_3
Harness
llama-bench
Prompt / output
512 / 0 tokens
Context
Not reported
Concurrency
1
Date
2026-05-16
Full record →
View
ReportGeneric LLM		GLM-4.7-FlashIQ4_XSModel ref. ↗Token speed—
2,995.47 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.0.0
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashQ8_0Model ref. ↗Token speed——
58.32 tok/sGeneration · unknown
1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Linux
Engine
llama.cpp
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
53 / 1024 tokens
Context
131072
Concurrency
Not reported
Date
2026-05-01
Full record →
View
ReportGeneric LLM		GLM-4.7-FlashQ4Model ref. ↗Token speed—
~2,690 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Windows 11 Pro 26200
Engine
Ollama
Backend
DirectML (author label; unverified)
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportCustom evaluation		GLM-4.7-FlashQ4_K_MModel ref. ↗Conflicting evidenceToken speedsynth-bulk-dispatcher-impl——
66.82 tok/sGeneration · mean · per request
2 × W7800Layer split · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Ubuntu 24.04 LTS
Engine
Ollama
Backend
ROCm
Harness
BoJl unified evaluation harness (2026-08)
Prompt / output
? / 4096 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashQ8_0Model ref. ↗Token speed——
93.28 tok/sGeneration · peak · unknown
3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Arch Linux
Engine
llama.cpp
Backend
vulkan
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
527 / 256 tokens
Context
783
Concurrency
Not reported
Date
2026-05-05
Full record →
View
Reportllama-bench		GLM-4.7-FlashBF16Model ref. ↗Token speed0 input tokens · 128 output tokens · 0 existing KV tokens——
23.17 tok/sGeneration · mean · per request
1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Fedora Linux 43 (Workstation Edition)
Engine
llama.cpp
Backend
ROCm / rocm-7_2_3
Harness
llama-bench
Prompt / output
0 / 128 tokens
Context
Not reported
Concurrency
1
Date
2026-05-16
Full record →
View
ReportGeneric LLM		GLM-4.7-FlashIQ4_XSModel ref. ↗Token speed—
2,967.89 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04
Engine
llama.cpp
Backend
ROCm 7.2.3
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-05-14
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashQ8_0Model ref. ↗Token speed——
82.57 tok/sGeneration · unknown
1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Linux
Engine
llama.cpp
Backend
vulkan
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
53 / 1024 tokens
Context
131072
Concurrency
Not reported
Date
2026-05-01
Full record →
View
ReportGeneric LLM		GLM-4.7-FlashQ4Model ref. ↗Token speed——
49.3 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Windows 11 Pro 26200
Engine
Ollama
Backend
DirectML (author label; unverified)
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportCustom evaluation		GLM-4.7-FlashQ4_K_MModel ref. ↗Conflicting evidenceToken speedsynth-horner-mpmath-derivative——
66.72 tok/sGeneration · mean · per request
2 × W7800Layer split · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Ubuntu 24.04 LTS
Engine
Ollama
Backend
ROCm
Harness
BoJl unified evaluation harness (2026-08)
Prompt / output
? / 4096 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashGPTQ-Int4-Int8MixModel ref. ↗Token speed——
211.92 tok/sGeneration · peak · unknown
3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Arch Linux
Engine
vllm
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
8512 / 4096 tokens
Context
32768
Concurrency
Not reported
Date
2026-05-16
Full record →
View
Reportllama-bench		GLM-4.7-FlashBF16Model ref. ↗Token speed2,048 input tokens · 0 output tokens · 32,768 existing KV tokens—
91.33 tok/sPrefill · mean · per request
—1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Fedora Linux 43 (Workstation Edition)
Engine
llama.cpp
Backend
ROCm / rocm-7_2_3
Harness
llama-bench
Prompt / output
2048 / 0 tokens
Context
Not reported
Concurrency
1
Date
2026-05-16
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashQ8_0Model ref. ↗Token speed——
39.69 tok/sGeneration · unknown
1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Linux
Engine
llama.cpp
Backend
vulkan
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
5888 / 2048 tokens
Context
262144
Concurrency
Not reported
Date
2026-04-28
Full record →
View
ReportGeneric LLM		GLM-4.7-FlashQ8_0Model ref. ↗Token speed—
~1,460 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Windows 11 Pro 26200
Engine
Ollama
Backend
DirectML (author label; unverified)
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportCustom evaluation		GLM-4.7-FlashQ4_K_MModel ref. ↗Conflicting evidenceToken speedsynth-invoke-sign-artifacts-ps——
67.78 tok/sGeneration · mean · per request
2 × W7800Layer split · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Ubuntu 24.04 LTS
Engine
Ollama
Backend
ROCm
Harness
BoJl unified evaluation harness (2026-08)
Prompt / output
? / 2980 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashGPTQ-Int4-Int8MixModel ref. ↗Token speed——
212.2 tok/sGeneration · unknown
3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Arch Linux
Engine
vllm
Backend
rocm
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
8512 / 4096 tokens
Context
32768
Concurrency
Not reported
Date
2026-05-16
Full record →
View
Reportllama-bench		GLM-4.7-FlashBF16Model ref. ↗Token speed0 input tokens · 32 output tokens · 32,768 existing KV tokens——
16.56 tok/sGeneration · mean · per request
1 × Ryzen AI Max+ 395Single GPU · Unified memory
Configuration
Memory
Unified memory
OS
Fedora Linux 43 (Workstation Edition)
Engine
llama.cpp
Backend
ROCm / rocm-7_2_3
Harness
llama-bench
Prompt / output
0 / 32 tokens
Context
Not reported
Concurrency
1
Date
2026-05-16
Full record →
View
ReportGeneric LLM		GLM-4.7-FlashQ8_0Model ref. ↗Token speed——
19.4 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Windows 11 Pro 26200
Engine
Ollama
Backend
DirectML (author label; unverified)
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportCustom evaluation		GLM-4.7-FlashQ4_K_MModel ref. ↗Conflicting evidenceToken speedsynth-legacy-rename-toolchain——
69.78 tok/sGeneration · mean · per request
2 × W7800Layer split · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Ubuntu 24.04 LTS
Engine
Ollama
Backend
ROCm
Harness
BoJl unified evaluation harness (2026-08)
Prompt / output
? / 1882 tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportLocalMaxxing		GLM-4.7-FlashMXFP4_MOEModel ref. ↗Token speed——
92.93 tok/sGeneration · peak · unknown
2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Arch Linux
Engine
llama.cpp
Backend
vulkan
Harness
LocalMaxxing community speed test; exact client where reported
Prompt / output
527 / 256 tokens
Context
783
Concurrency
Not reported
Date
2026-05-04
Full record →
Quantizations and software

Quantizations: BF16, GPTQ-Int4-Int8Mix, IQ4_XS, MXFP4_MOE, Q4, Q4_K_M, Q8_0, Q8_K_XL
Engines: llama.cpp, Ollama, vllm

Explore all 84 results →

This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports

GPU benchmark pages: W7800 · R9700 · RX 7700 XT · Ryzen AI Max+ 395