Muse Spark Open 816B A42B vs MiMo V2.6 Pro RL

MiMo V2.6 Pro RL leads llmrun Score 134.9 to 128.7 (ranges overlap); neither fits 24 GB.

Model A · Meta

Muse Spark Open 816B A42B

128.7llmrun Score

822.0B · 42B active · Other · Sep 2026

Vision

Model B · Xiaomi

MiMo V2.6 Pro RL

134.9llmrun Score

1020B · 42B active · 1M context · MIT · Sep 2026

ChatFunctions

Which should you choose?

Choose Muse Spark Open 816B A42B if you want…

Also does vision
MiMo V2.6 Pro RL doesn't list it

Choose MiMo V2.6 Pro RL if you want…

Higher llmrun Score
134.9 vs 128.7, ranges overlap
Also does chat, function-calling
Muse Spark Open 816B A42B doesn't list it
More permissive license
MIT vs Other

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

MemoryMuse Spark Open 816B A42BMiMo V2.6 Pro RL

8 GB

RTX 4060 · 8 GB tier

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

24 GBreference

RTX 4090 · 24 GB tier

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

32 GB

RTX 5090 · 32 GB tier

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

48 GB

RTX A6000 · 48 GB tier

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 32 GB

Mac Mini M4 · Macs

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Muse Spark Open 816B A42B

Doesn't fit

smallest quant needs 258.1 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).

llmrun Score

with its 90% range · bars share one scale

Muse Spark Open 816B A42B MiMo V2.6 Pro RL

Overall

Muse Spark Open 816B A42B

128.7125–132

MiMo V2.6 Pro RL

134.9131–138

Coding

Muse Spark Open 816B A42B

no data

MiMo V2.6 Pro RL

124.3115–133

Math

Muse Spark Open 816B A42B

128.4125–132

MiMo V2.6 Pro RL

no data

Science

Muse Spark Open 816B A42B

no data

MiMo V2.6 Pro RL

139.8129–151

Muse Spark Open 816B A42B · #7 of 94 open models · #5 of 90 that fit ≤640 GB

MiMo V2.6 Pro RL · #1 of 94 open models · #1 of 90 that fit ≤640 GB

Benchmarks

1 shared board: Muse Spark Open 816B A42B leads 0, MiMo V2.6 Pro RL leads 1 · Benchmarks imported Oct 2026

BoardMuse Spark Open 816B A42BMiMo V2.6 Pro RL

LMArena WebDev

Muse Spark Open 816B A42B

1511.3#13/52 open

ArenaLMArena · Oct 2026

MiMo V2.6 Pro RL

1624.8#5/52 open

ArenaLMArena · Oct 2026

11 more boards (other shared and single-model boards)

Only Muse Spark Open 816B A42B (5)

Only MiMo V2.6 Pro RL (6)

LMArena Text1479.2
SciCode60.9%
CritPt26.6%
APEX-Agents59.5%
ALE-Bench1158.1
ProofBench70.0%

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

QuantMuse Spark Open 816B A42BMiMo V2.6 Pro RL

Q2_K

Muse Spark Open 816B A42B

384 GB304.1 GB file

32K 404 GB · 128K 469 GB

MiMo V2.6 Pro RL

434 GB418.8 GB file

32K 437 GB · 128K 448 GB

Q3_K_M

Muse Spark Open 816B A42B

441 GB~400.7 GB file

32K 461 GB · 128K 525 GB

MiMo V2.6 Pro RL

498 GB~497.3 GB file

32K 501 GB · 128K 512 GB

Q4_0

Muse Spark Open 816B A42B

452 GB466.3 GB file

32K 472 GB · 128K 537 GB

MiMo V2.6 Pro RL

511 GB~510.0 GB file

32K 514 GB · 128K 524 GB

Q4_K_M

Muse Spark Open 816B A42B

543 GB~493.2 GB file

32K 563 GB · 128K 627 GB

MiMo V2.6 Pro RL

613 GB~612.0 GB file

32K 616 GB · 128K 626 GB

Q5_K_M

Muse Spark Open 816B A42B

644 GB~585.7 GB file

32K 664 GB · 128K 729 GB

MiMo V2.6 Pro RL

727 GB~726.8 GB file

32K 731 GB · 128K 741 GB

Q6_K

Muse Spark Open 816B A42B

746 GB~678.2 GB file

32K 766 GB · 128K 831 GB

MiMo V2.6 Pro RL

842 GB~841.5 GB file

32K 845 GB · 128K 856 GB

Q8_0

Muse Spark Open 816B A42B

904 GB871.6 GB file

32K 924 GB · 128K 989 GB

MiMo V2.6 Pro RL

1021 GB~1020.0 GB file

32K 1024 GB · 128K 1034 GB

5 more quants

IQ2_XXS

Muse Spark Open 816B A42B

249 GB225.6 GB file

32K 269 GB · 128K 333 GB

MiMo V2.6 Pro RL

not listed

IQ2_S

Muse Spark Open 816B A42B

283 GB275.5 GB file

32K 303 GB · 128K 367 GB

MiMo V2.6 Pro RL

not listed

IQ3_XXS

Muse Spark Open 816B A42B

350 GB340.4 GB file

32K 371 GB · 128K 435 GB

MiMo V2.6 Pro RL

not listed

Q4_K_S

Muse Spark Open 816B A42B

509 GB470.1 GB file

32K 529 GB · 128K 593 GB

MiMo V2.6 Pro RL

not listed

BF16

Muse Spark Open 816B A42B

1808 GB1640.3 GB file

32K 1829 GB · 128K 1893 GB

MiMo V2.6 Pro RL

2041 GB~2040.0 GB file

32K 2044 GB · 128K 2054 GB

How to run each

Muse Spark Open 816B A42B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Muse-Spark-Open-816B-A42B-GGUF

All ways to run Muse Spark Open 816B A42B →

MiMo V2.6 Pro RL

Ollama · Q4_K_M

$ollama run hf.co/ggml-org/MiMo-V2.6-Pro-RL-GGUF

All ways to run MiMo V2.6 Pro RL →

Specifications

Specifications of Muse Spark Open 816B A42B and MiMo V2.6 Pro RL
Spec	Muse Spark Open 816B A42B	MiMo V2.6 Pro RL
Publisher	Meta	Xiaomi
Parameters	822.0B	1020B
Active parameters	42B per token	42B per token
Architecture	—	MiMoV2ForCausalLM
Context	—	1M tokens
Modalities	Vision	Chat, Function-calling
License	Other	MIT
Released	Sep 2026	Sep 2026

Frequently Asked Questions

Which is better, Muse Spark Open 816B A42B or MiMo V2.6 Pro RL?

MiMo V2.6 Pro RL leads llmrun Score 134.9 to 128.7 (ranges overlap); neither fits 24 GB. Choose Muse Spark Open 816B A42B for also does vision; choose MiMo V2.6 Pro RL for higher llmrun Score and also does chat, function-calling.

Which needs less VRAM, Muse Spark Open 816B A42B or MiMo V2.6 Pro RL?

At Q4_K_M, Muse Spark Open 816B A42B requires 542.5 GB while MiMo V2.6 Pro RL needs 612.5 GB, making Muse Spark Open 816B A42B the easier model to run on your local setup.

Can I run Muse Spark Open 816B A42B or MiMo V2.6 Pro RL on a 16 GB GPU?

Muse Spark Open 816B A42B does not fit (smallest quant needs 258.1 GB); MiMo V2.6 Pro RL does not fit (smallest quant needs 435.6 GB).