Qwen3 Coder 480B A35B Instruct vs Beam 1.0 501B A23B
Beam 1.0 501B A23B leads llmrun Score 119.5 to 103.9; neither fits 24 GB.
Run Beam 1.0 501B A23B in the cloud →
Model A · Alibaba
Qwen3 Coder 480B A35B Instruct480.2B · 35.5B active · 256K context · Apache 2.0 · Jul 2025
Model B · reflection
Beam 1.0 501B A23B501.3B · 23.4B active · 1M context · Apache 2.0 · Oct 2026
Choose Beam 1.0 501B A23B if you want…
Higher llmrun Score
119.5 vs 103.9
Stronger at agents
118.3 vs 104.9
Longer context window
1M vs 256K tokens
Also does reasoning
Qwen3 Coder 480B A35B Instruct doesn't list it
Newer release
Oct 2026 vs Jul 2025
Qwen3 Coder 480B A35B Instruct: no clear edge over Beam 1.0 501B A23B in the data we have.
On your hardware
Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.
8 GB
RTX 4060 · 8 GB tier
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
12 GB
RTX 3060 12GB · 12 GB tier
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
24 GBreference
RTX 4090 · 24 GB tier
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
32 GB
RTX 5090 · 32 GB tier
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
48 GB
RTX A6000 · 48 GB tier
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
Mac 32 GB
Mac Mini M4 · Macs
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
Mac 64 GB
Mac Studio M4 Max · Macs
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
Mac 128 GB
Mac Studio M4 Max · Macs
Qwen3 Coder 480B A35B Instruct
Doesn't fit
smallest quant needs 146.4 GB
Beam 1.0 501B A23B
Doesn't fit
smallest quant needs 141.1 GB
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Qwen3 Coder 480B A35B Instruct
Beam 1.0 501B A23B
Coding
Qwen3 Coder 480B A35B Instruct
Beam 1.0 501B A23B
no data
Agents
Qwen3 Coder 480B A35B Instruct
Beam 1.0 501B A23B
Reasoning
Qwen3 Coder 480B A35B Instruct
no data
Beam 1.0 501B A23B
Qwen3 Coder 480B A35B Instruct · #47 of 106 open models · #43 of 102 that fit ≤512 GB
Beam 1.0 501B A23B · #17 of 106 open models · #14 of 102 that fit ≤512 GB
19 more boards (other shared and single-model boards)
Qwen3 Coder 480B A35B Instruct
1387.6#59/188 open
ArenaLMArena · Oct 2026
Beam 1.0 501B A23B
1435.7#23/188 open
ArenaLMArena · Oct 2026
Qwen3 Coder 480B A35B Instruct
1274.8#48/55 open
ArenaLMArena · Oct 2026
Beam 1.0 501B A23B
1436.0#25/55 open
ArenaLMArena · Oct 2026
Only Qwen3 Coder 480B A35B Instruct (6)
- SWE-bench Verified69.6%
- Terminal-Bench27.2%
- SWE-bench Bash Only55.4%
- WeirdML41.2%
- ALE-Bench461.4
- GSO-Bench4.9%
Only Beam 1.0 501B A23B (11)
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
Qwen3 Coder 480B A35B Instruct
205 GB174.7 GB file
32K 209 GB · 128K 221 GB
Beam 1.0 501B A23B
214 GB190.7 GB file
32K 219 GB · 128K 237 GB
Q3_K_S
Qwen3 Coder 480B A35B Instruct
211 GB206.9 GB file
32K 215 GB · 128K 227 GB
Beam 1.0 501B A23B
220 GB225.9 GB file
32K 225 GB · 128K 243 GB
Q3_K_M
Qwen3 Coder 480B A35B Instruct
235 GB229.2 GB file
32K 239 GB · 128K 251 GB
Beam 1.0 501B A23B
245 GB236.6 GB file
32K 250 GB · 128K 268 GB
Q4_0
Qwen3 Coder 480B A35B Instruct
241 GB271.6 GB file
32K 245 GB · 128K 257 GB
Beam 1.0 501B A23B
251 GB284.2 GB file
32K 257 GB · 128K 274 GB
Q4_K_M
Qwen3 Coder 480B A35B Instruct
289 GB290.1 GB file
32K 293 GB · 128K 305 GB
Beam 1.0 501B A23B
301 GB314.5 GB file
32K 307 GB · 128K 324 GB
Q5_K_M
Qwen3 Coder 480B A35B Instruct
343 GB340.5 GB file
32K 347 GB · 128K 359 GB
Beam 1.0 501B A23B
358 GB380.8 GB file
32K 363 GB · 128K 381 GB
Q6_K
Qwen3 Coder 480B A35B Instruct
397 GB394.1 GB file
32K 401 GB · 128K 413 GB
Beam 1.0 501B A23B
414 GB441.8 GB file
32K 420 GB · 128K 437 GB
Q8_0
Qwen3 Coder 480B A35B Instruct
481 GB510.4 GB file
32K 485 GB · 128K 497 GB
Beam 1.0 501B A23B
502 GB532.8 GB file
32K 507 GB · 128K 525 GB
14 more quants
IQ2_XXS
Qwen3 Coder 480B A35B Instruct
not listed
Beam 1.0 501B A23B
139 GB145.3 GB file
32K 144 GB · 128K 161 GB
IQ2_XS
Qwen3 Coder 480B A35B Instruct
145 GB132.9 GB file
32K 149 GB · 128K 161 GB
Beam 1.0 501B A23B
151 GB151.7 GB file
32K 156 GB · 128K 174 GB
IQ2_S
Qwen3 Coder 480B A35B Instruct
151 GB133.6 GB file
32K 155 GB · 128K 167 GB
Beam 1.0 501B A23B
157 GB161.3 GB file
32K 163 GB · 128K 180 GB
IQ2_M
Qwen3 Coder 480B A35B Instruct
not listed
Beam 1.0 501B A23B
170 GB178.5 GB file
32K 175 GB · 128K 193 GB
IQ3_XXS
Qwen3 Coder 480B A35B Instruct
187 GB201.5 GB file
32K 191 GB · 128K 203 GB
Beam 1.0 501B A23B
195 GB211.1 GB file
32K 200 GB · 128K 218 GB
IQ3_XS
Qwen3 Coder 480B A35B Instruct
199 GB197.1 GB file
32K 203 GB · 128K 215 GB
Beam 1.0 501B A23B
207 GB224.5 GB file
32K 213 GB · 128K 230 GB
IQ3_M
Qwen3 Coder 480B A35B Instruct
217 GB218.4 GB file
32K 221 GB · 128K 233 GB
Beam 1.0 501B A23B
226 GB255.7 GB file
32K 232 GB · 128K 249 GB
Q3_K_L
Qwen3 Coder 480B A35B Instruct
247 GB226.7 GB file
32K 251 GB · 128K 263 GB
Beam 1.0 501B A23B
258 GB249.5 GB file
32K 263 GB · 128K 280 GB
IQ4_XS
Qwen3 Coder 480B A35B Instruct
259 GB260.5 GB file
32K 263 GB · 128K 275 GB
Beam 1.0 501B A23B
270 GB273.1 GB file
32K 276 GB · 128K 293 GB
IQ4_NL
Qwen3 Coder 480B A35B Instruct
271 GB270.6 GB file
32K 275 GB · 128K 287 GB
Beam 1.0 501B A23B
283 GB311.9 GB file
32K 288 GB · 128K 306 GB
Q4_1
Qwen3 Coder 480B A35B Instruct
271 GB300.5 GB file
32K 275 GB · 128K 287 GB
Beam 1.0 501B A23B
283 GB314.1 GB file
32K 288 GB · 128K 306 GB
Q4_K_S
Qwen3 Coder 480B A35B Instruct
271 GB272.8 GB file
32K 275 GB · 128K 287 GB
Beam 1.0 501B A23B
283 GB293.4 GB file
32K 288 GB · 128K 306 GB
Q5_K_S
Qwen3 Coder 480B A35B Instruct
331 GB330.4 GB file
32K 335 GB · 128K 347 GB
Beam 1.0 501B A23B
345 GB355.1 GB file
32K 351 GB · 128K 368 GB
BF16
Qwen3 Coder 480B A35B Instruct
961 GB960.4 GB file
32K 965 GB · 128K 977 GB
Beam 1.0 501B A23B
1003 GB1002.7 GB file
32K 1009 GB · 128K 1026 GB
Qwen3 Coder 480B A35B Instruct
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:Q4_K_MBeam 1.0 501B A23B
Ollama · Q4_K_M
ollama run hf.co/bartowski/Beam-1.0-501B-A23B-GGUF:Q4_K_M| Spec | Qwen3 Coder 480B A35B Instruct | Beam 1.0 501B A23B |
|---|---|---|
| Publisher | Alibaba | reflection |
| Parameters | 480.2B | 501.3B |
| Active parameters | 35B per token | 23B per token |
| Architecture | Qwen3MoeForCausalLM | BeamForCausalLM |
| Context | 256K tokens | 1M tokens |
| Modalities | Chat, Code, Function-calling | Chat, Reasoning, Code, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Jul 2025 | Oct 2026 |
Frequently Asked Questions
Which is better, Qwen3 Coder 480B A35B Instruct or Beam 1.0 501B A23B?
Beam 1.0 501B A23B leads llmrun Score 119.5 to 103.9; neither fits 24 GB. Choose Beam 1.0 501B A23B for higher llmrun Score and stronger at agents.
Which needs less VRAM, Qwen3 Coder 480B A35B Instruct or Beam 1.0 501B A23B?
At Q4_K_M, Qwen3 Coder 480B A35B Instruct requires 288.7 GB while Beam 1.0 501B A23B needs 301.4 GB, making Qwen3 Coder 480B A35B Instruct the easier model to run on your local setup.
Can I run Qwen3 Coder 480B A35B Instruct or Beam 1.0 501B A23B on a 16 GB GPU?
Qwen3 Coder 480B A35B Instruct does not fit (smallest quant needs 146.4 GB); Beam 1.0 501B A23B does not fit (smallest quant needs 141.1 GB).
Which has a longer context window, Qwen3 Coder 480B A35B Instruct or Beam 1.0 501B A23B?
Qwen3 Coder 480B A35B Instruct supports 262,144 tokens and Beam 1.0 501B A23B supports 1,048,576 tokens.