LFM2 24B A2B vs Gemma 4 E4B IT vs Qwen3.5 4B
Too close to call on our weighted score (Qwen3.5 4B 78, Gemma 4 E4B IT 76, LFM2 24B A2B 58). The right pick depends on what you value most.
Liquid AILFM2 24B A2B
58/100- ECI—
- Price$0.03 / $0.12
- Context33K
GoogleGemma 4 E4B IT
76/100- ECI—
- Price$0.02 / $0.10
- Context131K
Alibaba (Qwen)Qwen3.5 4B
78/100- ECI—
- Price$0.04 / $0.07
- Context262K
Too close to call
It is close. Our weighted score puts them within 2 points (Qwen3.5 4B 78/100, Gemma 4 E4B IT 76/100, LFM2 24B A2B 58/100), so choose by what matters most for your work: Gemma 4 E4B IT on price and Qwen3.5 4B for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGemma 4 E4B ITGemma 4 E4B IT $0.04 · Qwen3.5 4B $0.048 · LFM2 24B A2B $0.052 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 4BQwen3.5 4B 262,144 · Gemma 4 E4B IT 131,072 · LFM2 24B A2B 32,768 tokens
- Widest inputsGemma 4 E4B IT and Qwen3.5 4BLFM2 24B A2B: Text · Gemma 4 E4B IT: Text, Images, Audio · Qwen3.5 4B: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | LFM2 24B A2B | Gemma 4 E4B IT | Qwen3.5 4B |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 25 | 70 | 70 |
| Context window | 20% | 0 | 25 | 37 |
| Overall | 100% | 58/100 | 76/100 | 78/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | LFM2 24B A2BLiquid AI | Gemma 4 E4B ITGoogle | Qwen3.5 4BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 55.8% |
| Price per million tokens | |||
| Input | $0.03 | $0.02 (best) | $0.04 |
| Output | $0.12 | $0.10 | $0.07 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.052 | $0.04 (best) | $0.048 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Median of 3 providers |
| Limits | |||
| Context window | 32,768 tokens | 131,072 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens | 8,192 tokens | 81,920 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | No | Yes |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenLFM Open License v1.0 | Open | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 1 | 2 | 5 (best) |
| Released | Feb 24, 2026 | Apr 2, 2026 | Mar 2, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- LFM2 24B A2B$0.54
- Gemma 4 E4B IT$0.40
- Qwen3.5 4B$0.54
Which should you choose?
Which is better: LFM2 24B A2B, Gemma 4 E4B IT or Qwen3.5 4B?
It is close. Our weighted score puts them within 2 points (Qwen3.5 4B 78/100, Gemma 4 E4B IT 76/100, LFM2 24B A2B 58/100), so choose by what matters most for your work: Gemma 4 E4B IT on price and Qwen3.5 4B for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, LFM2 24B A2B, Gemma 4 E4B IT or Qwen3.5 4B?
Gemma 4 E4B IT is cheaper at $0.02 input / $0.10 output per million tokens (median across 1 API provider). Qwen3.5 4B costs $0.04 input / $0.07 output per million tokens (median across 3 API providers); LFM2 24B A2B costs $0.03 input / $0.12 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.04 per million tokens for Gemma 4 E4B IT versus $0.048 for Qwen3.5 4B (1.2× as much) and $0.052 for LFM2 24B A2B (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. LFM2 24B A2B has not been scored yet, Gemma 4 E4B IT has not been scored yet and Qwen3.5 4B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for LFM2 24B A2B, Gemma 4 E4B IT and Qwen3.5 4B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Qwen3.5 4B has the largest context window at 262,144 tokens, against 131,072 for Gemma 4 E4B IT and 32,768 for LFM2 24B A2B. Maximum output per response: LFM2 24B A2B up to 32,768, Gemma 4 E4B IT up to 8,192, Qwen3.5 4B up to 81,920 tokens.
Which can read images, PDFs, audio or video?
LFM2 24B A2B accepts text; Gemma 4 E4B IT accepts text, images and audio; Qwen3.5 4B accepts text, images and video. Gemma 4 E4B IT handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (LFM Open License v1.0 and Apache-2.0), so you can self-host them.
Which is newer?
Gemma 4 E4B IT is the newest, released Apr 2, 2026. Qwen3.5 4B came out Mar 2, 2026; LFM2 24B A2B came out Feb 24, 2026.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
