C4ai Command A 03 2025 vs GPT OSS 120B
GPT OSS 120B leads llmrun Score 97.5 to 79.8; neither fits 24 GB.
Model B · OpenAI
GPT OSS 120B116.8B · 5.8B active · 128K context · Apache 2.0 · Aug 2025
Choose GPT OSS 120B if you want…
Higher llmrun Score
97.5 vs 79.8
Stronger at reasoning
95.9 vs 83.4
Ahead on the benchmarks
3 of 3 shared boards
More permissive license
Apache 2.0 vs CC BY-NC 4.0
Newer release
Aug 2025 vs Mar 2025
C4ai Command A 03 2025: no clear edge over GPT OSS 120B 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
C4ai Command A 03 2025
Doesn't fit
smallest quant needs 39 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
12 GB
RTX 3060 12GB · 12 GB tier
C4ai Command A 03 2025
Doesn't fit
smallest quant needs 39 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
C4ai Command A 03 2025
Doesn't fit
smallest quant needs 39 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
24 GBreference
RTX 4090 · 24 GB tier
C4ai Command A 03 2025
Doesn't fit
smallest quant needs 39 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
32 GB
RTX 5090 · 32 GB tier
C4ai Command A 03 2025
Doesn't fit
smallest quant needs 39 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
48 GB
RTX A6000 · 48 GB tier
C4ai Command A 03 2025
IQ2_M · ~12 tok/s
46.6 GB · up to 16K
GPT OSS 120B
IQ2_M · ~169 tok/s
40.2 GB · up to 128Kfaster
Mac 32 GB
Mac Mini M4 · Macs
C4ai Command A 03 2025
Doesn't fit
smallest quant needs 39 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
Mac 64 GB
Mac Studio M4 Max · Macs
C4ai Command A 03 2025
IQ3_M · ~7 tok/s
60.3 GB · up to 16K
GPT OSS 120B
Q4_0 · ~68 tok/s
59.1 GB · up to 64Kbetter quant
Mac 128 GB
Mac Studio M4 Max · Macs
C4ai Command A 03 2025
Q4_K_M · ~5 tok/s
78.7 GB · up to 32K
GPT OSS 120B
Q4_K_M · ~61 tok/s
70.8 GB · up to 128Kfaster
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
C4ai Command A 03 2025
GPT OSS 120B
Coding
C4ai Command A 03 2025
no data
GPT OSS 120B
Agents
C4ai Command A 03 2025
no data
GPT OSS 120B
Science
C4ai Command A 03 2025
no data
GPT OSS 120B
Reasoning
C4ai Command A 03 2025
GPT OSS 120B
C4ai Command A 03 2025 · #83 of 100 open models · #44 of 60 that fit ≤96 GB
GPT OSS 120B · #58 of 100 open models · #25 of 60 that fit ≤96 GB
Benchmarks
3 shared boards: C4ai Command A 03 2025 leads 0, GPT OSS 120B leads 3 · Benchmarks imported Oct 2026
C4ai Command A 03 2025
12.0%#16/18 open
IndependentEpoch AI · Mar 2025
GPT OSS 120B
41.8%#10/18 open
IndependentEpoch AI · Aug 2025
C4ai Command A 03 2025
61.3%#43/68 open
Lab-reportedEpoch AI · Mar 2025
GPT OSS 120B
76.3%#27/68 open
Lab-reportedEpoch AI · Aug 2025
C4ai Command A 03 2025
10.3%#47/54 open
Lab-reportedEpoch AI · Mar 2025
GPT OSS 120B
22.1%#32/54 open
Lab-reportedEpoch AI · Aug 2025
18 more boards (other shared and single-model boards)
C4ai Command A 03 2025
1353.7#73/187 open
ArenaLMArena · Oct 2026
GPT OSS 120B
1351.8#75/187 open
ArenaLMArena · Oct 2026
Only GPT OSS 120B (17)
- SWE-bench Verified26.0%
- GPQA Diamond75.8%
- AIME 2024/202588.9%
- Terminal-Bench18.7%
- MMLU-Pro80.8%
- SWE-bench Bash Only26.0%
- SciCode36.0%
- SimpleBench22.1%
- WeirdML48.2%
- APEX-Agents4.4%
- CritPt1.1%
- Fiction.LiveBench44.4%
- Mystery Game Puzzles2.0%
- Vending-Bench 2-21.5
- ALE-Bench575.6
- Surface Evolver Bench25.0%
- METR Time Horizons56.6%
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
C4ai Command A 03 2025
51.9 GB42.1 GB file
32K 63.4 GB · 128K 100 GB
GPT OSS 120B
50.1 GB62.6 GB file
32K 50.8 GB · 128K 53.4 GB
Q3_K_S
C4ai Command A 03 2025
53.5 GB49.0 GB file
32K 64.9 GB · 128K 102 GB
GPT OSS 120B
51.5 GB62.6 GB file
32K 52.3 GB · 128K 54.8 GB
Q3_K_M
C4ai Command A 03 2025
59.6 GB54.4 GB file
32K 71.0 GB · 128K 108 GB
GPT OSS 120B
57.4 GB62.6 GB file
32K 58.1 GB · 128K 60.7 GB
Q4_0
C4ai Command A 03 2025
61.1 GB63.5 GB file
32K 72.6 GB · 128K 109 GB
GPT OSS 120B
58.8 GB62.6 GB file
32K 59.6 GB · 128K 62.1 GB
Q4_K_M
C4ai Command A 03 2025
73.3 GB67.1 GB file
32K 84.8 GB · 128K 122 GB
GPT OSS 120B
70.5 GB62.8 GB file
32K 71.3 GB · 128K 73.8 GB
Q5_K_M
C4ai Command A 03 2025
87.0 GB78.8 GB file
32K 98.5 GB · 128K 135 GB
GPT OSS 120B
83.7 GB62.9 GB file
32K 84.4 GB · 128K 86.9 GB
Q6_K
C4ai Command A 03 2025
101 GB91.1 GB file
32K 112 GB · 128K 149 GB
GPT OSS 120B
96.8 GB63.3 GB file
32K 97.5 GB · 128K 100 GB
Q8_0
C4ai Command A 03 2025
122 GB118.0 GB file
32K 134 GB · 128K 170 GB
GPT OSS 120B
117 GB~116.8 GB file
32K 118 GB · 128K 121 GB
17 more quants
IQ2_XXS
C4ai Command A 03 2025
33.6 GB30.5 GB file
32K 45.1 GB · 128K 81.8 GB
GPT OSS 120B
not listed
IQ2_XS
C4ai Command A 03 2025
36.7 GB33.7 GB file
32K 48.1 GB · 128K 84.9 GB
GPT OSS 120B
not listed
IQ2_S
C4ai Command A 03 2025
38.2 GB35.5 GB file
32K 49.7 GB · 128K 86.4 GB
GPT OSS 120B
not listed
IQ2_M
C4ai Command A 03 2025
41.2 GB38.4 GB file
32K 52.7 GB · 128K 89.5 GB
GPT OSS 120B
39.8 GB~39.4 GB file
32K 40.6 GB · 128K 43.1 GB
IQ3_XXS
C4ai Command A 03 2025
47.3 GB43.4 GB file
32K 58.8 GB · 128K 95.6 GB
GPT OSS 120B
not listed
Q2_K_S
C4ai Command A 03 2025
48.9 GB39.0 GB file
32K 60.4 GB · 128K 97.1 GB
GPT OSS 120B
not listed
IQ3_XS
C4ai Command A 03 2025
50.4 GB46.5 GB file
32K 61.9 GB · 128K 98.6 GB
GPT OSS 120B
not listed
IQ3_S
C4ai Command A 03 2025
51.9 GB49.1 GB file
32K 63.4 GB · 128K 100 GB
GPT OSS 120B
not listed
IQ3_M
C4ai Command A 03 2025
55.0 GB50.8 GB file
32K 66.5 GB · 128K 103 GB
GPT OSS 120B
53.0 GB62.7 GB file
32K 53.7 GB · 128K 56.3 GB
Q3_K_L
C4ai Command A 03 2025
62.6 GB59.1 GB file
32K 74.1 GB · 128K 111 GB
GPT OSS 120B
60.3 GB62.6 GB file
32K 61.0 GB · 128K 63.6 GB
IQ4_XS
C4ai Command A 03 2025
65.7 GB60.0 GB file
32K 77.2 GB · 128K 114 GB
GPT OSS 120B
63.2 GB62.7 GB file
32K 64.0 GB · 128K 66.5 GB
IQ4_NL
C4ai Command A 03 2025
68.7 GB63.4 GB file
32K 80.2 GB · 128K 117 GB
GPT OSS 120B
66.1 GB62.7 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_1
C4ai Command A 03 2025
68.7 GB70.0 GB file
32K 80.2 GB · 128K 117 GB
GPT OSS 120B
66.1 GB62.7 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_K_S
C4ai Command A 03 2025
68.7 GB63.8 GB file
32K 80.2 GB · 128K 117 GB
GPT OSS 120B
66.1 GB62.8 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_K_L
C4ai Command A 03 2025
74.8 GB67.9 GB file
32K 86.3 GB · 128K 123 GB
GPT OSS 120B
72.0 GB63.1 GB file
32K 72.7 GB · 128K 75.3 GB
Q5_K_S
C4ai Command A 03 2025
84.0 GB76.8 GB file
32K 95.5 GB · 128K 132 GB
GPT OSS 120B
80.7 GB62.9 GB file
32K 81.5 GB · 128K 84.0 GB
BF16
C4ai Command A 03 2025
244 GB222.1 GB file
32K 256 GB · 128K 293 GB
GPT OSS 120B
234 GB~233.7 GB file
32K 235 GB · 128K 237 GB
C4ai Command A 03 2025
Ollama · Q4_K_M
ollama run hf.co/bartowski/CohereForAI_c4ai-command-a-03-2025-GGUF:Q4_K_MGPT OSS 120B
Ollama · Q4_K_M
ollama run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M| Spec | C4ai Command A 03 2025 | GPT OSS 120B |
|---|---|---|
| Publisher | Cohere | OpenAI |
| Parameters | 111.1B | 116.8B |
| Active parameters | — | 5.8B per token |
| Architecture | — | GptOssForCausalLM |
| Context | — | 128K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | CC BY-NC 4.0 | Apache 2.0 |
| Released | Mar 2025 | Aug 2025 |
Frequently Asked Questions
Which is better, C4ai Command A 03 2025 or GPT OSS 120B?
GPT OSS 120B leads llmrun Score 97.5 to 79.8; neither fits 24 GB. Choose GPT OSS 120B for higher llmrun Score and stronger at reasoning.
Which needs less VRAM, C4ai Command A 03 2025 or GPT OSS 120B?
At Q4_K_M, C4ai Command A 03 2025 requires 73.3 GB while GPT OSS 120B needs 70.5 GB, making GPT OSS 120B the easier model to run on your local setup.
Can I run C4ai Command A 03 2025 or GPT OSS 120B on a 16 GB GPU?
C4ai Command A 03 2025 does not fit (smallest quant needs 39 GB); GPT OSS 120B does not fit (smallest quant needs 40.2 GB).