Alibaba / model
Qwen3.8 Flash Next
Unsloth UD-Q4_K_XL GGUF, revision f5d175d, running on NVIDIA DGX Spark, 128 GB.
27.7tok/sWriting speed, short prompt
7.6hoursTime for all 27 attempts
104GBFile size
Highlights
Qwen in Qwen3.8 Flash Next vs Hy4 Flash
From its roasts
Attempt 1, in fullIf I ask it to roast me, it would write a LinkedIn post about resilience and call it spicy.
A game it wrote

These games were written for a keyboard and a big screen. On a phone they may not respond. They are best on a computer.
Test 01 / Pilot
Results in Qwen3.8 Flash Next vs Hy4 Flash
Pelican on a bicycle
Opinion
- Valid drawings, of 3 attempts
- 3
Octopus and penguin band
Opinion
- Valid drawings, of 3 attempts
- 3
Playable browser game
Automatic load test; the rest is opinion
- Complete games
- 2 of 3 (1 cut off at the answer limit)
Roast
Opinion
- My ranking (opinion)
- Place 3 of 3
Text adventure
Rules check plus opinion
- Complete games
- 3 of 3
Bug fix
Hidden tests, automatic
- Bugs fixed of 3, per attempt
- 3, 3, 3
- Minutes per attempt
- 26 to 33
Contract questions
Answer key
- Score of 5, per attempt
- 4, 5, 5
- Slip
- Attempt 1 read the wrong row of the service credit table: DKK 248 where the answer is DKK 496.
12 steps with a contradiction
Answer key
- Flagged the contradiction
- 1 of 3
- Arithmetic right
- 3 of 3
Network design
Opinion
- Words per plan
- about 5,000
- Access points proposed
- 4 to 12
Every attempt, with time and tokens
| Challenge | Attempt | Status | Minutes | Tokens |
|---|---|---|---|---|
| Playable browser game | 1 | Finished | 32.1 | 51,099 |
| Playable browser game | 2 | Cut off at the answer limit | 37.8 | 60,000 |
| Playable browser game | 3 | Finished | 30.2 | 48,213 |
| Bug fix | 1 | Finished | 25.6 | 40,897 |
| Bug fix | 2 | Finished | 32.7 | 51,937 |
| Bug fix | 3 | Finished | 25.8 | 41,338 |
| Network design | 1 | Finished | 27.2 | 43,453 |
| Network design | 2 | Finished | 22.7 | 36,379 |
| Network design | 3 | Finished | 24.8 | 39,709 |
| Contract questions | 1 | Finished | 11.9 | 19,053 |
| Contract questions | 2 | Finished | 14.5 | 23,341 |
| Contract questions | 3 | Finished | 13.7 | 21,957 |
| 12 steps with a contradiction | 1 | Finished | 5.8 | 9,399 |
| 12 steps with a contradiction | 2 | Finished | 3.9 | 6,418 |
| 12 steps with a contradiction | 3 | Finished | 3.5 | 5,657 |
| Pelican on a bicycle | 1 | Finished | 9.2 | 14,981 |
| Pelican on a bicycle | 2 | Finished | 8.9 | 14,481 |
| Pelican on a bicycle | 3 | Finished | 11.1 | 17,998 |
| Octopus and penguin band | 1 | Finished | 18.6 | 30,074 |
| Octopus and penguin band | 2 | Finished | 22.3 | 35,913 |
| Octopus and penguin band | 3 | Finished | 25.1 | 40,185 |
| Roast | 1 | Finished | 4.3 | 7,053 |
| Roast | 2 | Finished | 3.1 | 5,153 |
| Roast | 3 | Finished | 1.2 | 1,961 |
| Text adventure | 1 | Finished | 13.0 | 21,000 |
| Text adventure | 2 | Finished | 16.6 | 26,802 |
| Text adventure | 3 | Finished | 10.8 | 17,314 |
Build and settings
What exactly ran
- Maker
- Alibaba
- Build
- Unsloth UD-Q4_K_XL GGUF, revision f5d175d
- File size
- 104 GB
- Machine
- NVIDIA DGX Spark, 128 GB
- Runtime
- llama.cpp 2cbca38 with the Hy4 Spark patch
- Sampling
- temperature 1.0, top-p 0.95, top-k 20 (maker thinking-mode settings)
- Thinking
- on (default)
Speed
How fast it ran here
- Writing speed, short prompt
- 27.7 tok/s
- Writing speed after a 32K prompt
- 25.9 tok/s
- Writing speed after a 127K prompt
- 23.9 tok/s
- Reading speed, 32K prompt
- 970 tok/s
- Reading speed, 127K prompt
- 933 tok/s
- Wait for first token, 32K prompt
- 33 s
- Wait for first token, 127K prompt
- 136 s (2.3 min)
- Load time
- 97 s (1.6 min)
- Least memory left free
- 7 GiB
- Time for all 27 attempts
- 7.6 hours
- Tokens generated, all attempts
- 731,765 tokens
- Short-prompt writing speed is the average of three runs; long-prompt rows are one run each.
- Hy4 Flash speed rows come from the first pilot night (same files and runtime); Qwen rows from the rerun on the current build.
- Speed tests use one fixed sampling setting for every model.
- About nine tenths of what all three models wrote was thinking, not answer.