Mistral Medium 3.5 128B vs GPT OSS 120B
Mistral Medium 3.5 128B leads llmrun Score 102.1 to 97.5 (ranges overlap); neither fits 24 GB.
Run Mistral Medium 3.5 128B in the cloud →
Model A · Mistral AI
Mistral Medium 3.5 128B127.7B · 256K context · Other · Mar 2026
Model B · OpenAI
GPT OSS 120B116.8B · 5.8B active · 128K context · Apache 2.0 · Aug 2025
Choose Mistral Medium 3.5 128B if you want…
Higher llmrun Score
102.1 vs 97.5, ranges overlap
Longer context window
256K vs 128K tokens
Newer release
Mar 2026 vs Aug 2025
Choose GPT OSS 120B if you want…
More permissive license
Apache 2.0 vs Other
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
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
12 GB
RTX 3060 12GB · 12 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
24 GBreference
RTX 4090 · 24 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
32 GB
RTX 5090 · 32 GB tier
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
48 GB
RTX A6000 · 48 GB tier
Mistral Medium 3.5 128B
IQ2_S · ~12 tok/s
46.1 GB · up to 16K
GPT OSS 120B
IQ2_M · ~169 tok/s
40.2 GB · up to 128K
Mac 32 GB
Mac Mini M4 · Macs
Mistral Medium 3.5 128B
Doesn't fit
smallest quant needs 41.3 GB
GPT OSS 120B
Doesn't fit
smallest quant needs 40.2 GB
Mac 64 GB
Mac Studio M4 Max · Macs
Mistral Medium 3.5 128B
IQ3_S · ~7 tok/s
60.5 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
Mistral Medium 3.5 128B
Q4_K_M · ~5 tok/s
82.8 GB · up to 128K
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
Mistral Medium 3.5 128B
GPT OSS 120B
Coding
Mistral Medium 3.5 128B
GPT OSS 120B
Agents
Mistral Medium 3.5 128B
no data
GPT OSS 120B
Science
Mistral Medium 3.5 128B
GPT OSS 120B
Reasoning
Mistral Medium 3.5 128B
GPT OSS 120B
Mistral Medium 3.5 128B · #53 of 106 open models · #20 of 62 that fit ≤96 GB
GPT OSS 120B · #66 of 106 open models · #28 of 62 that fit ≤96 GB
Benchmarks
7 shared boards: Mistral Medium 3.5 128B leads 4, GPT OSS 120B leads 3 · Benchmarks imported Nov 2026
Mistral Medium 3.5 128B
40.2%#36/72 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 120B
36.0%#51/72 open
Lab-reportedEpoch AI · Aug 2025
Mistral Medium 3.5 128B
43.7%#16/47 open
IndependentEpoch AI · Apr 2026
GPT OSS 120B
48.2%#11/47 open
IndependentEpoch AI · Aug 2025
Mistral Medium 3.5 128B
764.0#24/48 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 120B
575.6#34/48 open
Lab-reportedEpoch AI · Aug 2025
Mistral Medium 3.5 128B
0.0%#73/84 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 120B
1.1%#37/84 open
Lab-reportedEpoch AI · Aug 2025
Mistral Medium 3.5 128B
75.5%#30/70 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 120B
76.3%#28/70 open
Lab-reportedEpoch AI · Aug 2025
Mistral Medium 3.5 128B
26.1%#28/56 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 120B
22.1%#34/56 open
Lab-reportedEpoch AI · Aug 2025
Mistral Medium 3.5 128B
26.9%#12/15 open
Lab-reportedEpoch AI · Apr 2026
GPT OSS 120B
25.0%#13/15 open
Lab-reportedEpoch AI · Aug 2025
17 more boards (other shared and single-model boards)
Mistral Medium 3.5 128B
1426.4#28/188 open
ArenaLMArena · Oct 2026
GPT OSS 120B
1351.7#77/188 open
ArenaLMArena · Oct 2026
Only Mistral Medium 3.5 128B (3)
- LMArena WebDev1264.0
- FrontierCode8.0%
- ProofBench9.0%
Only GPT OSS 120B (13)
- SWE-bench Verified26.0%
- GPQA Diamond75.8%
- AIME 2024/202588.9%
- Terminal-Bench18.7%
- MMLU-Pro80.8%
- Aider Polyglot41.8%
- SWE-bench Bash Only26.0%
- SimpleBench22.1%
- APEX-Agents4.4%
- Fiction.LiveBench44.4%
- Mystery Game Puzzles2.0%
- Vending-Bench 2-21.5
- 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
Mistral Medium 3.5 128B
55.3 GB46.6 GB file
32K 66.4 GB · 128K 102 GB
GPT OSS 120B
50.1 GB62.6 GB file
32K 50.8 GB · 128K 53.4 GB
Q3_K_S
Mistral Medium 3.5 128B
56.9 GB54.4 GB file
32K 68.0 GB · 128K 103 GB
GPT OSS 120B
51.5 GB62.6 GB file
32K 52.3 GB · 128K 54.8 GB
Q3_K_M
Mistral Medium 3.5 128B
63.3 GB60.6 GB file
32K 74.4 GB · 128K 110 GB
GPT OSS 120B
57.4 GB62.6 GB file
32K 58.1 GB · 128K 60.7 GB
Q4_0
Mistral Medium 3.5 128B
64.9 GB71.0 GB file
32K 76.0 GB · 128K 111 GB
GPT OSS 120B
58.8 GB62.6 GB file
32K 59.6 GB · 128K 62.1 GB
Q4_K_M
Mistral Medium 3.5 128B
77.7 GB74.9 GB file
32K 88.7 GB · 128K 124 GB
GPT OSS 120B
70.5 GB62.8 GB file
32K 71.3 GB · 128K 73.8 GB
Q5_K_M
Mistral Medium 3.5 128B
92.0 GB88.3 GB file
32K 103 GB · 128K 139 GB
GPT OSS 120B
83.7 GB62.9 GB file
32K 84.4 GB · 128K 86.9 GB
Q6_K
Mistral Medium 3.5 128B
106 GB102.6 GB file
32K 117 GB · 128K 153 GB
GPT OSS 120B
96.8 GB63.3 GB file
32K 97.5 GB · 128K 100 GB
Q8_0
Mistral Medium 3.5 128B
129 GB132.9 GB file
32K 140 GB · 128K 175 GB
GPT OSS 120B
117 GB~116.8 GB file
32K 118 GB · 128K 121 GB
18 more quants
IQ2_XXS
Mistral Medium 3.5 128B
36.2 GB34.9 GB file
32K 47.2 GB · 128K 82.7 GB
GPT OSS 120B
not listed
IQ2_XS
Mistral Medium 3.5 128B
39.4 GB43.4 GB file
32K 50.4 GB · 128K 85.9 GB
GPT OSS 120B
not listed
IQ2_S
Mistral Medium 3.5 128B
41.0 GB46.1 GB file
32K 52.0 GB · 128K 87.5 GB
GPT OSS 120B
not listed
IQ2_M
Mistral Medium 3.5 128B
44.1 GB44.1 GB file
32K 55.2 GB · 128K 90.7 GB
GPT OSS 120B
39.8 GB~39.4 GB file
32K 40.6 GB · 128K 43.1 GB
IQ3_XXS
Mistral Medium 3.5 128B
50.5 GB49.3 GB file
32K 61.6 GB · 128K 97.0 GB
GPT OSS 120B
not listed
Q2_K_S
Mistral Medium 3.5 128B
52.1 GB43.0 GB file
32K 63.2 GB · 128K 98.6 GB
GPT OSS 120B
not listed
IQ3_XS
Mistral Medium 3.5 128B
53.7 GB54.9 GB file
32K 64.8 GB · 128K 100 GB
GPT OSS 120B
not listed
IQ3_S
Mistral Medium 3.5 128B
55.3 GB54.5 GB file
32K 66.4 GB · 128K 102 GB
GPT OSS 120B
not listed
IQ3_M
Mistral Medium 3.5 128B
58.5 GB59.5 GB file
32K 69.6 GB · 128K 105 GB
GPT OSS 120B
53.0 GB62.7 GB file
32K 53.7 GB · 128K 56.3 GB
Q3_K_L
Mistral Medium 3.5 128B
66.5 GB67.0 GB file
32K 77.6 GB · 128K 113 GB
GPT OSS 120B
60.3 GB62.6 GB file
32K 61.0 GB · 128K 63.6 GB
IQ4_XS
Mistral Medium 3.5 128B
69.7 GB67.1 GB file
32K 80.8 GB · 128K 116 GB
GPT OSS 120B
63.2 GB62.7 GB file
32K 64.0 GB · 128K 66.5 GB
IQ4_NL
Mistral Medium 3.5 128B
72.9 GB70.9 GB file
32K 83.9 GB · 128K 119 GB
GPT OSS 120B
66.1 GB62.7 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_1
Mistral Medium 3.5 128B
72.9 GB78.5 GB file
32K 83.9 GB · 128K 119 GB
GPT OSS 120B
66.1 GB62.7 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_K_S
Mistral Medium 3.5 128B
72.9 GB71.2 GB file
32K 83.9 GB · 128K 119 GB
GPT OSS 120B
66.1 GB62.8 GB file
32K 66.9 GB · 128K 69.4 GB
Q4_K_L
Mistral Medium 3.5 128B
79.3 GB79.6 GB file
32K 90.3 GB · 128K 126 GB
GPT OSS 120B
72.0 GB63.1 GB file
32K 72.7 GB · 128K 75.3 GB
Q5_K_S
Mistral Medium 3.5 128B
88.8 GB86.2 GB file
32K 99.9 GB · 128K 135 GB
GPT OSS 120B
80.7 GB62.9 GB file
32K 81.5 GB · 128K 84.0 GB
Q5_K_L
Mistral Medium 3.5 128B
93.6 GB92.1 GB file
32K 105 GB · 128K 140 GB
GPT OSS 120B
not listed
BF16
Mistral Medium 3.5 128B
256 GB250.1 GB file
32K 268 GB · 128K 303 GB
GPT OSS 120B
234 GB~233.7 GB file
32K 235 GB · 128K 237 GB
Mistral Medium 3.5 128B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_K_MGPT OSS 120B
Ollama · Q4_K_M
ollama run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M| Spec | Mistral Medium 3.5 128B | GPT OSS 120B |
|---|---|---|
| Publisher | Mistral AI | OpenAI |
| Parameters | 127.7B | 116.8B |
| Active parameters | — | 5.8B per token |
| Architecture | Mistral3ForConditionalGeneration | GptOssForCausalLM |
| Context | 256K tokens | 128K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Other | Apache 2.0 |
| Released | Mar 2026 | Aug 2025 |
Frequently Asked Questions
Which is better, Mistral Medium 3.5 128B or GPT OSS 120B?
Mistral Medium 3.5 128B leads llmrun Score 102.1 to 97.5 (ranges overlap); neither fits 24 GB. Choose Mistral Medium 3.5 128B for higher llmrun Score and longer context window; choose GPT OSS 120B for more permissive license.
Which needs less VRAM, Mistral Medium 3.5 128B or GPT OSS 120B?
At Q4_K_M, Mistral Medium 3.5 128B requires 77.7 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 Mistral Medium 3.5 128B or GPT OSS 120B on a 16 GB GPU?
Mistral Medium 3.5 128B does not fit (smallest quant needs 41.3 GB); GPT OSS 120B does not fit (smallest quant needs 40.2 GB).
Which has a longer context window, Mistral Medium 3.5 128B or GPT OSS 120B?
Mistral Medium 3.5 128B supports 262,144 tokens and GPT OSS 120B supports 131,072 tokens.