Community performance summary

Qwen3.6 35B A3B

15 GPU configurations measured with this model. Compare hardware differences, quantizations and every recorded result.

47 signed runs · 2 verified · 20 testers
Median prompt287.01tok/s · 24.35 to 1438.6
Median generation25tok/s · 7.85 to 71.02
Configurations6Q4_K_S · UD-IQ4_XS · UD-Q2_K_XL
Last observedSep 16GCN / Vega · GCN / Vega + RDNA 2 · RDNA 1 · RDNA 2 · Unknown

What the results show

One clear view.
Every recorded run.

Measurements from comparable hardware and models are presented together. Medians show typical performance, while every signed run remains available below for inspection and sharing.

Hardware tested15 groups
AMD Radeon Pro 5500M7 runsAMD Radeon RX 6700 XT2 runsAMD Radeon Pro 5600M3 runsAMD Radeon PRO W6800X Duo4 runsAMD Radeon PRO W6800X Duo ×28 runsAMD Radeon Pro W5700X ×21 runAMD Radeon Pro 5700 XT4 runsAMD Radeon Pro Vega II Duo1 runAMD Radeon Pro Vega II3 runsAMD Radeon RX Ellesmere Prototype3 runsAMD Radeon PRO W6800X2 runsAMD Radeon VII1 run
macOS

macOS 15.2 Sequoia · macOS 15.6.1 Sequoia · macOS 15.7.3 Sequoia · macOS 15.7.7 Sequoia · macOS 15.7.8 Sequoia · macOS 15.7.9 Sequoia · macOS 26.5 Tahoe · macOS 26.5.2 Tahoe · macOS 26.6 Tahoe · macOS 26.6.1 Tahoe · macOS 26.6.2 Tahoe

Recorded evidence

Inspect every run.

Open any result to review its exact hardware, model configuration, measurements and submission details.

1 to 8 of 47 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1253.18tok/s
71.02tok/s
chafeyAug 25, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1262.58tok/s
70.86tok/s
PixlaAug 29, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1254.93tok/s
70.69tok/s
chafeyAug 23, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1082.36tok/s
63.55tok/s
BirdsLikeWiresJul 22, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1143.21tok/s
63.38tok/s
PixlaAug 2, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1156.32tok/s
63.26tok/s
XanthousJul 28, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1139.23tok/s
63.14tok/s
Flint IronstagAug 22, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1171.32tok/s
62.94tok/s
Flint IronstagAug 22, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1086.98tok/s
55.79tok/s
PixlaAug 2, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1102.7tok/s
55.75tok/s
Flint IronstagAug 11, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
952.42tok/s
54.76tok/s
Flint IronstagJul 18, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
940.75tok/s
54.54tok/s
Flint IronstagJul 18, 2026
Qwen3.6 35B-A3BUD-Q4_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 1
704.73tok/s
46.53tok/s
HypabolicAug 12, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
280.34tok/s
42.24tok/s
gervaiscoquilJul 18, 2026
Qwen3.6 35B A3BQ4_K_S · MoE · All experts in VRAM · comparison
GCN / Vega
284.7tok/s
42.1tok/s
Mac Pro communityJul 16, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
432.42tok/s
41.97tok/s
ToshLLM communityAug 4, 2026
Qwen3.6 35B-A3BUD-Q8_K_XL · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega
320.65tok/s
41.94tok/s
ToshLLM communityAug 5, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 10 · amd-gpu · Metal · comparison
RDNA 1
194.85tok/s
33.5tok/s
tmnJul 18, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
426.35tok/s
31.28tok/s
Flint IronstagJul 20, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 17 · amd-gpu · Metal · comparison
RDNA 1
341.07tok/s
29.09tok/s
tmnJul 18, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 16 · amd-gpu · Metal · comparison
RDNA 1
348.2tok/s
29.06tok/s
tmnJul 18, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 16 · amd-gpu · Metal · comparison
RDNA 1
368.16tok/s
27.49tok/s
Aaron.CAug 11, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 24 · amd-gpu · Metal · comparison
RDNA 2
473.74tok/s
27.34tok/s
ToshLLM LabSep 11, 2026
Qwen3.6 35B A3BQ4_K_S · MoE · CPU expert offload · comparison
RX 6700 XT12 GB VRAM
RDNA 2
434tok/s
25tok/s
ToshLLM LabJul 15, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon Vega ×463.94 GB VRAM
GCN / Vega
237.43tok/s
20.22tok/s
Flint IronstagJul 20, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 2
167.83tok/s
20.06tok/s
test1-Henbury-DIsableJul 20, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 2
164.3tok/s
19.86tok/s
ardentwheelJul 19, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 2
166.97tok/s
19.51tok/s
test0-Henbury-DIsableJul 20, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 2
1438.6tok/s
19.48tok/s
PixlaAug 29, 2026
Qwen3.6 35B-A3BUD-Q2_K_XL · MoE · Signed ToshLLM app · ncmoe 23 · amd-gpu · Metal · comparison
RDNA 1
287.01tok/s
16.88tok/s
ToshLLM communitySep 7, 2026
Qwen3.6 35B-A3BUD-Q4_K_M · MoE · Signed ToshLLM app · ncmoe 35 · amd-gpu · Metal · comparison
RDNA 1
141.93tok/s
15.79tok/s
ToshLLM communitySep 10, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 2
164.7tok/s
14.07tok/s
ardentwheelJul 18, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 2
164.44tok/s
14.03tok/s
test1-Henbury-EnableJul 20, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 2
164.13tok/s
13.97tok/s
test0-Henbury-EnableJul 20, 2026
Qwen3.6 35B-A3BUD-Q4_K_M · MoE · Signed ToshLLM app · ncmoe 35 · amd-gpu · Metal · comparison
RDNA 1
141.58tok/s
13.96tok/s
ToshLLM communitySep 10, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 30 · amd-gpu · Metal · comparison
RDNA 1
148.47tok/s
13.21tok/s
ToshLLM communitySep 5, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 30 · amd-gpu · Metal · comparison
RDNA 1
148.37tok/s
13.09tok/s
oldwongSep 16, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 30 · amd-gpu · Metal · comparison
RDNA 1
149.38tok/s
13.05tok/s
ToshLLM communitySep 5, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 1
141.19tok/s
12.86tok/s
ToshLLM communitySep 4, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 1
141.28tok/s
12.44tok/s
oldwongSep 16, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 16 · amd-gpu · Metal · comparison
RDNA 2
471.86tok/s
11.84tok/s
ToshLLM communityAug 22, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 1
140.53tok/s
11.7tok/s
mnerdAug 26, 2026
Qwen3.6 35B-A3BUD-IQ4_XS · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
AMD Radeon VII15.98 GB VRAM
GCN / Vega
26.84tok/s
10.63tok/s
1252erJul 21, 2026
Qwen3.6 35B-A3BUD-IQ4_XS · MoE · Signed ToshLLM app · ncmoe 10 · amd-gpu · Metal · comparison
Unknown
25.65tok/s
10.31tok/s
1252erJul 21, 2026
Qwen3.6 35B-A3BUD-IQ4_XS · MoE · Signed ToshLLM app · ncmoe 6 · amd-gpu · Metal · comparison
Unknown
24.35tok/s
10.23tok/s
1252erAug 2, 2026
Qwen3.6 35B-A3BUD-Q4_K_S · MoE · Signed ToshLLM app · ncmoe 33 · amd-gpu · Metal · comparison
RDNA 1
132.78tok/s
10.14tok/s
mnerdJul 30, 2026
Qwen3.6 35B-A3BUD-IQ4_XS · MoE · Signed ToshLLM app · ncmoe 25 · amd-gpu · Metal · comparison
Unknown
74.01tok/s
7.85tok/s
1252erAug 2, 2026