Reviews
The short version
- Qwen3 Next 80B A3B Thinking is a free model from Alibaba's Qwen team that you can run on your own computer. In our tests it's not one we'd recommend right now: 31 out of 100, #50 of 63.
- It solved 8 of 30 coding jobs and scored 36 on reading documents. On our hardest tasks it scored 20.
- Runs on a Mac with 96 GB.
Coding
Our coding test is 30 programming jobs, from small ones like reading time durations or cleaning up messy data to harder ones like a config-file parser or a double-entry ledger. We run each answer against tests the model never sees, and a job only counts if everything passes. Qwen3 Next 80B A3B Thinking got 8 of 30 right. The best local coders solved 29 of 30.
Reading documents
The second test hands the model things like an expense claim thread, a pay stub or an insurance statement, and asks for specific numbers and dates. Many questions need a bit of math, or noticing a correction further down the email. Qwen3 Next 80B A3B Thinking scored 36; the best model scored 100.
| Test | Score | Public questions | Secret questions |
|---|---|---|---|
| Coding | 27 | 14 | 30 |
| Reading documents | 36 | 20 | 40 |
| Decisions | 41 | 57 | 36 |
On the 18 hardest tasks (included in the scores above) it scored 20. This number separates the top models.
This model did much better on our public questions than on the secret ones. Sometimes that's luck; it can also mean the model has seen the public questions before.
We tested the full-size version online. The smaller versions you download usually score a little lower.
Can your computer run it?
You can download Qwen3 Next 80B A3B Thinking in several sizes. Smaller versions fit on more computers and lose a little quality, so pick the biggest one that fits.
| Your computer | Runs it? | Version to download |
|---|---|---|
| Graphics card, 8 GB | No | – |
| Graphics card, 12 GB | No | – |
| Graphics card, 16 GB | No | – |
| Graphics card, 24 GB | No | – |
| Graphics card, 32 GB | No | – |
| Mac, 16 GB | No | – |
| Mac, 24 GB | No | – |
| Mac, 32 GB | No | – |
| Mac, 48 GB | No | – |
| Mac, 64 GB | No | – |
| Mac, 96 GB | Yes | Q6 |
| Mac, 128 GB | Yes | Q8 |
For normal-length chats. Long documents need more memory. Q4 or Q8? · How we worked this out
How to try it
Search for "Qwen3 Next 80B A3B Thinking GGUF" in LM Studio or on Hugging Face and pick the version that fits your computer. New to this? Start with our Ollama guide.
Want the strongest all-rounder instead? Qwen3.6 27B scored 97.
Its actual answers
What Qwen3 Next 80B A3B Thinking wrote for our public questions, word for word.
Coding: INI parser (hard) Didn't work
Coding: TTL LRU (hard) Didn't work
```python
from collections import OrderedDict
class TTL Cache:
def __init__(self, capacity: int, ttl: float, clock):
self.capacity = capacity
self.ttl = ttl
self.clock = clock
self.stats = {'hits': 0, 'misses': 0, 'evictions': 0, 'expirations': 0}
self.cache = OrderedDict()
def put(self, key, value):
if self.capacity == 0:
return
if key in self.cache:
current_time = self.clock()
new_expiration = current_time + self.ttl
self.cache[key] = (value, new_expiration)
self.cache.move_to_end(key)
return
current_time = self.clock()
if len(self.cache) >= self.capacity:
expired_keys = []
for k in list(self.cache.keys()):
if current_time >= self.cache[k][1]:
expired_keys.append(k)
for k in expired_keys:
del self.cache[k]
self.stats['expirations'] += 1
if len(self.cache) >= self.capacity:
lru_key = next(iter(self.cache.keys()))
del self.cache[lru_key]
self.stats['evictions'] += 1
new_expiration = current_time + self.ttl
self.cache[key] = (value, new_expiration)
self.cache.move_to_end(key)
def get(self, key, default=None):
if self.capacity == 0:
self.stats[' misses'] += 1
return default
current_time = self.clock()
if key in self.cache:
value, expiration_time = self.cache[key]
if current_time >= expiration_time:
del self.cache[key]
self.stats['expirations'] += 1
self.stats[' misses'] += 1
return default
else:
self.cache.move_to_end(key)
self.stats['hits'] += 1
return value
else:
self.stats[' misses'] += 1
return default
def __len__(self):
current_time = self.clock()
count = 0
for key in self.cache:
if current_time < self.cache[key][1]:
count += 1
return count
def stats(self):
return self.stats.copy()
```Coding: Parse duration Didn't work
Coding: Summarize ranges Didn't work
```python
def summarize ranges(nums: list[int]) -> str:
if not nums:
return ""
sortednums = sorted(set(nums))
start = sortednums[0]
current = start
res = []
for i in range(1, len(sortednums)):
if sortednums[i] == current + 1:
current = sortednums[i]
else:
if current - start >= 2:
res.append(f"{start}..{current}")
elif current - start == 1:
res.append(str(start))
res.append(str(current))
else:
res.append(str(start))
start = sortednums[i]
current = start
if current - start >= 2:
res.append(f"{start}..{current}")
elif current - start == 1:
res.append(str(start))
res.append(str(current))
else:
res.append(str(start))
return ','.join(res)
```Coding: Top customers Didn't work
Coding: Slugify Didn't work
Coding: Token bucket Worked
```python
class TokenBucket:
def __init__(self, capacity: float, refill_per_sec: float, clock):
self.capacity = capacity
self.refill_per_sec = refill_per_sec
self.clock = clock
self._tokens = capacity
self.last_refill = clock()
def _refill(self):
current_time = self.clock()
elapsed = current_time - self.last_refill
add_tokens = elapsed * self.refill_per_sec
self._tokens = min(self.capacity, self._tokens + add_tokens)
self.last_refill = current_time
@property
def tokens(self):
self._refill()
return self._tokens
def allow(self, cost: float = 1) -> bool:
self._refill()
if self._tokens >= cost:
self._tokens -= cost
return True
return False
```Decisions: Refund window (hard) 100% right
{
"outcome": {
"full_refund": 0.0,
"partial_refund": 0.0,
"store_credit": 1.0,
"nothing": 0.0
},
"defective": {
"true": 0.0,
"false": 1.0
}
}Decisions: Incident matrix (hard) 0% right
{
" severity": {
"0": 0.0,
"1": 1.0,
"2": 0.0,
"3": 0.0
},
" page": {
" true": 0.0,
" false": 1.0
}
}Decisions: Tool followup (hard) 0% right
Decisions: Legit security alert (hard) 100% right
{
"phishing": {
"true": 0.0,
"false": 1.0
},
"action_needed": {
"true": 0.0,
"false": 1.0
}
}Decisions: Meeting slot (hard) 100% right
{"slot":{"A":0.0,"B":1.0,"C":0.0,"D":0.0},"raj_last":{"true":1.0," false":0.0}}Decisions: Review mixed (hard) 100% right
{
"hardware": {
"true": 1.0,
"false": 0.0
},
"support": {
"true": 1.0,
"false": 0.0
}
}Decisions: Support checkout down 0% right
Decisions: Refund wrong plan 0% right
{"department":{" billing":1.0," technical":0.0," account":0.0,"shipping":0.0,"sales":0.0}," refund":{"true":1.0," false":0.0}," tone":{" frustrated":0.0," calm":1.0}}Decisions: Moderation doxxing 0% right
Decisions: Route calendar 100% right
{"tool":{"web_search":0.0," calculator":0.0,"calendar":1.0,"email":0.0,"none":0.0},"confirm":{"true":1.0,"false":0.0}}Decisions: Doc invoice missing due 100% right
{
"doc_type": {
"invoice": 1.0,
"resume": 0.0,
"contract": 0.0,
"bank_statement": 0.0,
"其他": 0.0
},
"missing_due_date": {
"true": 1.0,
"false": 0.0
}
}Decisions: Phishing paypal 100% right
{
"phishing": {
"true": 1.0,
"false": 0.0
},
"risk": {
"0": 0.0,
"1": 0.0,
"2": 0.0,
"3": 1.0
}
}Decisions: Pii ssn email 100% right
{"data_kind":{" none":0.0,"contact":0.0," financial":0.0,"government_id":1.0," health":0.0},"sensitive":{"true":1.0,"false":0.0}}Decisions: Review mixed 0% right
Documents: Saas escalator (hard) 0% right
Documents: Expense thread 0% right
Documents: Lease amendment 0% right
Documents: Ticket SLA 0% right
Documents: Sales footnotes 100% right
{"q3_total_usd":15346000,"q2_total_usd":14464000,"q2_central_originally_reported_usd":3047000,"q2_to_q3_change_pct":6.1,"top_region_q3":"East","fastest_growing_region_q1_to_q3":"International","regions_declining_q2_to_q3":["East"],"international_q3_organic_usd":1731000,"west_excluding_mountain_q3_usd":4201000}Size: 81B parameters. First tested OCT 11.
Comments
Sign in with GitHub to comment. Spam and abuse are hidden automatically.